IS484 IS Project Experience (FinTech)

This is an SMU-X course designed in collaboration with participating Banks, FinTechs, and other FIs, to serve as project sponsors. Collectively, industry sponsors will supply a minimum of 5 projects ideas to select from.
Students will form teams of 5 or 6, and select one the project ideas to work on. Project selections do not need to be unique, meaning multiple teams can select the same project idea.
Each student project team will be assigned to a sponsor/mentor and an SMU faculty supervisor.
Sponsors will provide project scope and management for student teams to have practical industry learning experiences.
Student teams will have weekly check in meetings, either virtually or physically, with their sponsor.
Sponsors will specify the technologies to be used, including; development tools/languages, OS, database, 3rd party libraries, target deployment environment e.g. cloud environment.
Student project teams will be expected to develop a working software application prototype, to be delivered to the sponsor at the end of the course.

Course Prerequisites:

1. Software Project Management (IS212) is a pre-requisite or a co-requisite.
2. Any two (2) track courses from the track that you are declaring for your project. One of these courses can be a co-requisite.

Project Timeline:

Activities	Timeline	Term 1/ Term 2	Action By
Project Sourcing and Registration	Week -14 to Week -10	Form teams. Review the below set of predefined projects provided by Citibank, OCBC, NETS, UBS, and others. Fill up the Project Team Signup Sheet at the below link, listing your preferred projects. FT Track Coordinator will finalize the matching of teams to projects.	Students
Project Matching	Week -10	FT Track Coordinator will finalize the matching of teams to projects.	FT Track Coordinator
Proposal	Due before the start of Week -8	Submit your project proposals to your Track Coordinator(s). For mixed-track teams, both track coordinators need to review your proposal.	Students
Decision on Proposal	Week -4	Your Track Coordinator(s) will confirm that the project has sufficient scope to fulfill your respective track requirements for IS Project Experience.	Track Coordinator, Students, (Optional: Sponsor)
Start of Project	Week 1	Supervisor - Teams	Student
Midterm	Week 8	Presentation	Students, Supervisor, Reviewer (Optional: Sponsor, Track Coordinator)
Finals	Week 14 to Week 16	Presentation	Students, Supervisor, Reviewer (Optional: Sponsor, Track Coordinator)

Project Team Signup Sheet:

AY2024/25 Term 1
https://docs.google.com/spreadsheets/d/1IDAhC4JiK3RuKnIDQMG5UjJ6I1IiImo81Lu13wAuUxE/edit#gid=491663198
AY2024/25 Term 2
https://docs.google.com/spreadsheets/d/1q-2qNkXGcjPxybU52s-1cazP5k4zhHTYRn7SKxz5Hjg/edit?gid=0#gid=0

Current Projects - FY2024/25 Term 2

ID and Term

Sponsor / Business Vertical

Project Description

Project Scope

Project Stakeholders

Briefing Session Schedule

Project #1

FY2024/25
Term 2

OCBC - Consumer Banking

Fast Data Acquisition for Real-time Analytics
Core Banking processes a high volume of customer transactions including transfers, deposits and payments in an RDBMS (say PostgreSQL). There is a need to analyze the data real-time to detect any anomalies and generate operational reports. The application transaction database in optimized for high-availability and write performance, not analytics.

Therefore, there is a need for a real-time ingestion framework to stream transaction data from the source to the target operational data store (ODS), for real-time analytics.

Traditional batch ETL processes result in delayed data availability, leading to slower decision-making. Real-time analytics improves the customer

service, reduce fraud risk etc.

The key challenges that should be address are

Low latency: Data needs to be streamed in near real-time without impacting the performance of the source transaction system.

Data consistency: The data arriving at the ODS remains consistent with the source system, especially during high transaction volumes.

Scalability: The ingestion framework must scale to handle increasing transaction volumes during peak hours, like flash sales or promotions etc.

High Availability: The framework should tolerate failures and be resilient with high-availability.

Project Inputs:
Project sponsors will share sufficient context so students can understand how/where this model brings value to users.

Project Deliverables:

• A low latency real-time ingestion framework using CDC and should support CRUD operations to be consistent with the source database.

• Analytics dashboard that provides insights as

• Customer activity and behaviour

• Pending or failed payments

• Total transaction volume per minute/hour

• Documentation with detailed setup instructions for configuring the ingestion with no-coding and just using configuration changes.

Project Coordinator: Lim Wei Ming
Project Mentor:

Radhakrishna Sarma

TBC

Project #2

FY2024/25
Term 2

OCBC - Front Office Relationship Managers

Front Office Dashboard / Client meeting prep support

The goal of this project is to leverage GenAI Technologies to develop a dashboard and client meeting preparation support system. The system will gather relevant information such as to-do lists, insights that clients would appreciate, follow-ups from previous meetings, outstanding document deficiencies, and areas requiring client feedback. All of this information will be consolidated into a meeting preparation pack, making it easier for professionals to prepare for client meetings efficiently.

Front office staff often struggle to gather and organize all the necessary information for client meetings. This leads to inefficiencies and potential oversights. Therefore, there is a need for a system that can streamline the process of gathering, organizing, and presenting important information to professionals before client meetings.

Project Inputs:

• Project sponsors will share sufficient context so students can understand how/where this UI brings value to users.

• Components required for effective client meeting preparation, including to-do lists, insights, follow-ups, document deficiencies, reviews, and client feedback.

• Data or resources necessary for testing, such as sample client meeting data, client feedbacks, digital channel access data and relevant documents.

Project Deliverables:

• Dashboard: Create a user-friendly dashboard that allows Front office to input and access information for client meeting preparation.

• AI Integration: Utilize GenAI Technologies to enhance the system's capabilities, such as natural language processing for analyzing meeting notes and predictive analytics for generating insights.

• Data Analysis: Implement AI models to analyze data inputs and generate valuable insights, such as identifying patterns in client feedback or predicting potential document deficiencies.

• Meeting Preparation Pack: Consolidate all relevant information, including to-do lists, insights, follow-ups, document deficiencies, reviews, and areas requiring client feedback, into a comprehensive meeting preparation pack.

Project Coordinator: Bryan Lee Cheng Hui

Project Mentor: Amila Silva

TBC

Project #3

FY2024/25
Term 2

OCBC - Group Operations & Technology

This project aims to explore the concept of Zero-Knowledge Rollups, an innovative technology that addresses two significant challenges in blockchain transactions: privacy and efficiency. In simpler terms, Zero-Knowledge Rollups are like a secret code that allows you to do more things securely and quickly without anyone

else knowing the details.

In the world of digital currencies and blockchain, it's crucial to ensure that transactions are both private and efficient. Zero-Knowledge Rollups offer a promising solution by bundling many transactions together and proving they are valid without revealing specific details about each individual transaction.

This approach enables blockchain networks to handle a large number of transactions at once, making them faster and more scalable. This also prove that transactions are valid without exposing the specifics. As a practical demonstration, we are able to develop blockchain applications such as:

1. Enhancing Privacy and Scalability in Blockchain Transactions using Zero-Knowledge Rollups

There is a need for an improved solution to address the privacy and scalability challenges facing blockchain transactions. Traditional blockchain systems, such as those used in cryptocurrencies, often struggle to handle a high volume of transactions while simultaneously ensuring the privacy of participants.

Existing blockchain architectures suffer from limited scalability, resulting in congestion and increased transaction delay during peak usage periods. Moreover, transaction details are often visible to malicious actors, compromising user privacy and confidentiality.

Project Inputs:

• Project sponsors will share sufficient context so students can understand its use cases, discussing the benefits and limitations of implementing zero knowledge rollups and how it can benefit end users.

• The project details, explanation of the zero knowledge rollups and other useful details will be shared.

Project Deliverables:

• Students will dive into the technical aspects of Zero-Knowledge proofs, learn about the challenges of implementing Rollup solutions, and examine real-world examples where this technology has been used successfully

• Investigate where zero knowledge rollups can be applied in banking environment. Students will study relevant academic resources, examine existing Zero-Knowledge Rollup implementations

• Create simulations or proof-of-concept prototypes to explore the practical aspects

Project Coordinator: Ravindra Kumar

Project Mentor: Jorden Seet

TBC

Project #4

FY2024/25
Term 2

Citi - Exchange Traded & Cleared Derivatives

Collateral Optimization for CCP Margin Calls

Citi provides its clients with clearing services on several global Central Counterparty Clearing Houses (CCPs). Clients can post eligible currency (cash) & financial instruments (bonds, treasury notes, securities, commodity warrants, etc.) as collateral to cover margin calls. Citi, as a clearing member, will then utilize some of these assets to cover the corresponding margin calls with the CCP.

Each CCP has specific requirements regarding the types of collateral it accepts, applying different haircuts and collateral fees based on asset class. Additionally, transaction costs are incurred when depositing, substituting or withdrawing collateral. Optimizing the allocation of available collateral across different CCPs can minimize costs and increase efficiency.

This project aims to develop an algorithm that optimizes the allocation of available collateral to various CCPs based on eligibility, collateral costs, haircuts, and transaction costs, taking into account frequent changes in available collateral due to client activity.

Citi’s clearing services require optimal collateral allocation to different CCPs in order to minimize costs and comply with eligibility requirements. The current process involves multiple variables such as collateral eligibility, haircut rates, collateral fees, and transaction costs. The objective of this project is to build a solution that optimizes collateral allocation for margin calls at each CCP while minimizing associated costs and fees.

Project Inputs:

Students will be provided with:

1. A file containing a list of available collateral.

2. A file that lists the margin calls required at each CCP.

3. A file containing static data regarding eligible

associated haircut rates, fees, and transaction costs at different CCPs.

All required data is in public domain. No Citi proprietary data is required nor will be shared for this project.

Project Deliverables:

1. Optimization Algorithm: A solution to optimize the allocation of available collateral across multiple CCPs based on eligibility, costs, and transaction considerations.

2. User Interface: A basic user interface to input data and visualize the optimized collateral allocation across CCPs.

3. Collateral Movement Report: A user report that lists the optimal collateral allocation and the related asset movements.

4. Documentation: Detailed documentation explaining the methodology, logic behind the optimization algorithm, and any assumptions made.

5. Presentation: A final presentation demonstrating the optimization tool, its functionality, and potential real-world applications for Citi's operations.

Project Coordinator: TBA

Project Mentor: Nirav Parikh

TBC

Project #5

FY2024/25
Term 2

Citi - Markets & Trading

Synthetic Market Generator for Algorithmic Trading

One of the key challenges in training trading algorithms is the limited availability of real-world historical data specific to certain securities. This scarcity of data can lead to overfitting and suboptimal performance in machine learning models. Moreover, it is difficult to find data that accurately reflects specific market conditions, including varying volumes, trends, and volatility levels.

This project aims to address these challenges by developing a synthetic market simulator capable of generating market data tailored to specific securities and market conditions. The simulator will be parameterized to model various patterns, volatility levels, and market trends, providing a flexible tool for creating synthetic datasets. These datasets can then be used for training and testing algorithmic trading strategies, avoiding the pitfalls of limited real-world data.

Current trading models face the challenge of limited historical data for specific securities and market conditions. This project seeks to build a synthetic market data simulator that allows traders and researchers to generate customized market data based on chosen parameters such as volatility, trend strength, and volume. This will provide a larger and more diverse dataset to train trading algorithms, leading to better generalization and performance in various market environments.

Project Inputs:

Students will be provided with:

1. A representative set of market data for a given security (historical OHLCV data).

2. Parameters to tune the synthetic data generation, including market patterns, volatility, trends, and volume.

All required data is in public domain. No Citi proprietary data is required nor will be shared for this project.

Project Deliverables:

1. Synthetic Data Generator: A working model that simulates and outputs synthetic market data based on input parameters.

2. Parameterization: A set of controls to modify the synthetic data generation, including trend types, volatility levels, and other key market conditions.

3. Transaction Output: The output will be a file containing the generated market data, with fields such as Open, High, Low, Close, and Volume (OHLCV).

4. Documentation: Detailed documentation explaining how the synthetic data is generated, how to use the parameterization tools, and how the simulator can be applied in algorithm training.

5. Presentation: A demonstration of the synthetic market simulator, including use cases for improving trading algorithm performance.

Project Coordinator: TBA

Project Mentor: Nirav Parikh

TBC

Project #6

FY2024/25
Term 2

Citi - Investment Banking

Deal Review Committee Using LLM Agents

In investment banking, evaluating deals for new clients involves multiple dimensions of analysis. Banks must assess the market potential, competitive positioning, and risk profile of a client’s business, while estimating revenue and cost projections. Additionally, ensuring compliance with regulatory standards and aligning deals with the bank’s strategic objectives are crucial aspects of decision-making.

This project proposes the development of a framework utilizing Large Language Model (LLM) agents to simulate a virtual committee of financial experts. Each LLM agent will be specialized in specific areas such as risk assessment (credit, market, operational, regulatory, reputational), revenue estimation, compliance, and strategic alignment. By simulating the expertise of real-world financial analysts and risk managers, this system will provide a comprehensive review of deal proposals for new clients.

The goal is to enhance decision-making, mitigate risks, ensure regulatory compliance, and foster profitable client relationships, helping banks balance opportunity with risk for long-term sustainability and growth.

Investment banks face challenges in evaluating deal proposals due to the need for multi-faceted analysis across revenue potential, risk assessment, regulatory compliance, and strategic fit. This project aims to develop a framework leveraging LLM agents to provide a holistic and expert-driven approach to deal review, improving both the efficiency and accuracy of decision- making processes.

Project Inputs:

Students will be provided with:

1. Training data from previous deal reviews, including analysis from financial analysts and risk managers.

2. Access to relevant market data, risk factors, and financial models.

3. Strategic guidelines and risk appetite documentation for new deals.

Note: Anonymized Citi internal data (no client data) will be required for this project subject to approvals and potential NDA agreements.

Project Deliverables:

1. LLM-Based Expert Agents: A framework of specialized LLM agents trained to simulate expert perspectives in areas such as revenue estimation, risk analysis, compliance, and strategic alignment.

2. Virtual Committee Decision Process: A mechanism for synthesizing the insights from different agents to form a comprehensive recommendation on deal approval and conditions.

3. Decision Support System: A tool that provides deal recommendations, approval conditions, and risk mitigation strategies based on the committee’s output.

4. Documentation: Comprehensive documentation outlining the design, methodology, and decision-making process of the virtual committee of LLM agents.

5. Presentation: A final presentation showcasing the framework, its decision-making process, and its potential impact on the bank's deal review process.

Project Coordinator: TBA

Project Mentor: Nirav Parikh

TBC

Project #7

FY2024/25
Term 2

Revolut - Digital Investing

Bespoke Robo Advisory Platform for Retail Users

Create a digital investment platform that allows users to invest into through Revolut’s Robo-advisory solution coupled with the Users own inputs relating to Risk Appetite, preferred asset class mix, single name stocks and investment amount.

The ask is to create a web app that:

• Allows users to include more inputs before letting Robo advisory take over the investment of users funds.

• List of investment instruments and asset classes available

• Visualize the performance data using charts, tables etc. in a simple, uncluttered fashion.

Robo-advisory is a useful solution / tool for beginning and intermediate investors who wise to utilize ”Robos” to optimize users funds and invest accordingly based on black box algorithms built by the Robo Advisory company.

The Problem is that users have little or no say in which specific asset class, industries, or single name stocks should the investor have a preference in whilst offering the investor expertise of the Robo Advisory perform dynamic asset re-allocation as and when the need to do arises.

So the idea is to create a platform which is a hybrid of a Robo-Advisor and a full manual trading platform

Project Inputs:

• Project sponsors will share sufficient context so students can understand how/where this platform brings value to users.

• The mock raw data files, explanation of this data structure and other useful details will be available.

Project Deliverables:

• Working App that provides intuitive UI/UX.

• This App should be a standalone application that can be easily incorporated in a larger application. Freedom to use visualization & analysis tools, technology of the team’s choice.

Project Coordinator: [ TBA ]

Project Mentor: Abhinav Suryavanshi

TBC

Project #8 FY2024/25

Term 2

Singapura Finance -Regulatory Compliance

Customer Profiling Application

Customers are on-boarded to the bank’s system after performing checks and validation for know your customer and anti-money laundering (KYC/AML) compliance.

The solution should extract information about existing customers, run checks and document results. It will score each customer based on given parameters. The parameters may change over time, so flexibility to adjust the parameter will be required.

The current approach to handling AML scoring and documenting of customer profile is manually done by staff. It is not consistent and prone to oversight and missing filed information.

Project Inputs:

• Project sponsors will share context so students can understand how/where this digitalization can add value to the organization.

• The mock up data and parameter for scoring will be shared with explanation on the digital filing requirements.

• Potential to use ML Tools to profile customer

Project Deliverables:

A solution or program which can accomplish the following:

• Take in a customer information from the banking system

• Profile the customer information using available search/information engine/service provider. Obtain the results

• Decipher the results obtained

• Score each customer profile

• Store the results for historical review or audit review requirement.

• Allow customization of the scoring

• Easy search and identification of customer profile documents collated.

• Allow for triggering of review on customer information based on score

Project Coordinator: (TBA)

Project Mentor: Winny Ho

TBC

Project #9

FY2024/25
Term 2

Singapura Finance - Risk Management

Consumer Loans Credit Scoring

The bank implemented an online straight through loan application (Mortgage) using government provided information, with customers consent.

The system does not identify nor prioritize customer profile, hence good/great customers are left together with the majority.

Solution will use information obtained by the government data source and generate a credit score each application. An application may have more than one submission (Multiple owners).

The solution should provide automated recommendation for improved loan rates for of better scoring customers. It should also document and recommend follow-up for lower scoring applications.

Project Inputs:

• Project sponsors will share context so students can understand how/where this digitalization can add value to the organization.

• The mock up data and parameter for scoring will be shared with explanation on the digital filing requirements.

Project Deliverables:

An app that provides the following:

• Take in a customer information submitted via online forms/government data.

• Profile the customer information

• Analyze the results obtained and score each application

• Allow customization of the scoring using various data points available.

• Results will be sent to back-room for processing or automated escalated actions.

Project Coordinator: (TBA)

Project Mentor: Cindy Ng

TBC

Project #10

FY2024/25
Term 2

Tiger Fund - Fund Management

Using Artificial Intelligence for Effective Stock Screening

This project focuses on using artificial intelligence (AI) to develop an effective stock screening tool that assists investors in identifying potential buying or selling opportunities in the U.S. stock market.

With the vast amount of data generated daily, AI can automate the screening process by quickly analyzing stock trends, sector performance, and user-defined parameters to detect valuable market opportunities.

The system will leverage machine learning algorithms and technical indicators to filter stocks based on investor preferences, such as undervaluation, technical patterns, or strong market trends.

The goal is to streamline stock selection and improve decision-making efficiency for portfolio managers.

Investors face a challenge in sorting through the immense quantity of stock market data to identify opportunities for profitable trading. The manual stock screening process is time-consuming and prone to human error, especially when considering various technical indicators and market conditions.

This project aims to address these issues by developing an AI-powered stock screening system capable of efficiently analyzing stock data, detecting strong market trends, and automating the identification of potential buying or selling opportunities based on predefined criteria.

Project Inputs:

• Project sponsors will share sufficient context so students can understand how/where this project brings value to users.

Project Deliverables:

• AI-Powered Stock Screener Application: A functional application that can analyze large datasets and apply user-defined parameters to screen stocks.

• Backtesting: To engage in backtesting of the model in order to ensure the reliability of the system

• Market Trend Detection Module: A feature that detects strong market trends or significant changes in sector performance.

• Sector Analysis Tool: A tool to conduct in-depth analysis of sectors to identify potential opportunities for buying recommendations.

• Sentiment Analysis Engine: A system that scrapes and analyzes sentiment data from news articles, social media, and financial reports, and integrates it into the model.

• User Interface for Stock Screening: An interactive interface where users can input their screening criteria and view stock recommendations in real-time.

Project Coordinator: [TBA]

Project Mentor: [TBA]

TBC

Project #11

FY2024/25
Term 2

Tiger Fund - Fund Management

Using Artificial Intelligence to Time the Market

The project aims to build a machine learning-based system that assists portfolio managers with accurate market timing by predicting the prices of major Exchange-Traded Funds (ETFs) such as SPY (S&P 500 ETF) and TLT (Treasury Bond ETF).

The core component of this system will be an AI model, potentially using a Long Short-Term Memory (LSTM) neural network, which will predict future prices based on a blend of economic, fundamental, sentiment, and technical data.

The model will be designed to continuously learn and adapt to evolving financial environments, making real-time predictions.

The data inputs will be aggregated from reliable financial sources like FRED, World Bank, Yahoo Finance, and sentiment analysis from news outlets, social media, and financial reports to develop a comprehensive model.

Accurate market timing is one of the most challenging tasks for portfolio managers. Market prices fluctuate based on a wide range of factors, including economic indicators, fundamental analysis, market sentiment, and technical trends. Traditional financial models often fail to capture the complexity and rapid changes in market dynamics. This project seeks to bridge the gap by leveraging machine learning to forecast ETF prices more accurately and continuously adapt to changing market conditions.

Project Inputs:

• Project sponsors will share sufficient context so students can understand how/where this project brings value to users.

Project Deliverables:

• AI Prediction Model: A machine learning model trained to predict the prices of SPY and TLT based on technical, economic, fundamental, and sentiment data. An AI system capable of retraining itself as new data becomes available, allowing for adaptation to market changes.

• Backtesting: To engage in backtesting of the model in order to ensure the reliability of the system

• Sentiment Analysis Engine: A system that scrapes and analyzes sentiment data from news articles, social media, and financial reports, and integrates it into the model.

• Risk Appetite Indicator: A composite indicator driven by sentiment analysis, measuring market risk aversion or appetite to inform predictions.

• Data Pipeline: Web scraping and integration pipeline to pull continuous data from FRED, World Bank, Yahoo Finance, and other relevant sources.

• Dashboard Interface: A user-friendly dashboard to display model predictions, risk appetite indicators, and relevant metrics.

Project Coordinator: [TBA]

Project Mentor: [TBA]

TBC

Project #12

FY2024/25
Term 2

UBS - Equities

News Screener For Relevant Investment Opportunities

Bankers and Investment counselors (ICs) develop deep relationships with clients and provide them with relevant investment and opportunities advices based on client’s needs.

The ask is to create a tool that:
Scans publicly available social media and news sources for news about relevant sector’s or region’s current and ongoing events and their co-related relevant companies or entities.

Summarize these views to a digestible format for Client Advisor, Ensure each data point has a source link, that would enable the Client Advisor to verify that the subject is indeed relevant to preferences of their client.

Freedom to use visualization & analysis tools, generative AI, APIs and technology of the team’s choice. However the solution should be hosted in an Azure Cloud.

Example: Tools scans news from the ‘Financial Times’ for relevant sector ‘Real Estate’ and region ‘China’, Based on the news coverage, it identifies the current market trend and effected companies and instruments relevant to those companies and provides a relevant view to client advisors.

Given current volatile world and lots of information being generated every moment, analysts require smart intelligent tools to sort through all those and provide clients with relevant investment advices on timely manner. The tool is to automated way to scan news, provide digest about the news in categories like sector, region and entity. Also to provide relevant sentiment of the news.

Project Inputs:

• Project sponsors will provide 5 entity names, and suggested data sources on which the output should be created

• Project Sponsors will review at regular intervals the outputs to refine requirements and usability of output.

• We will provide support on how to perform identity matching for the entities.

• Team can use AI tools to discover digest of news (e.g. news is about ‘Real Estate’ sector.)

Project Deliverables:

• Working dashboard that provides a real view of relevant sectors and entities.

• View provides contextual correlated sentiment assessment of entities.

• View provides trigger notifications when significant activity threshold is breached (optional).

• View provides collected historical information and perform system end to end risk and returns on entities.

• Ability to collect data from different sources.

Project Coordinator: Kumar, Ajith-A

Project Mentor: Hossain, Mohammad-Jahangir

TBC

Project #13

FY2024/25
Term 2

UBS - Mobile banking

Modern web application and Native Mobile application for

Portfolio viewing of a banking customer

There are already a quite a lot of Banking asset viewing and portfolio viewing apps in the market currently. Having a great user experience for such apps are key for success of any business. User experience is garnered from Customer experience strategy, research and design. Understanding user behavior and human computer interaction techniques are key in designing and implementing next gen user experience application is key.

In this project you will produce native iOS/Android mobile application and web application using latest technology which inculcates great customer experience design , user experience design and wireframes. There are already great deal of research materials on this subject, so need a both balanced academic view and already existing app view to come out with a great application to do portfolio viewing of a Banking clients assets. The backend may have mock data to begin with so not really expecting the app to work end to end. Key success criteria are to have a great visual and customer experience for these apps.

This project aims to develop a banking portfolio viewing application which targets the upcoming generation of banking application consumers, ie. Gen Z and Millennials. Additionally, we will enhance the user experience of our application by implementing specific design considerations obtained through rigorous user research and analysis of human-computer interactions.

Project Inputs:

• Technology services mentor will provide insights on deep knowledge on the subject

• Help students to formulate the solution ideation

• Provide the expertise where necessary for the group to produce a industry standard solution

Project Deliverables:

Must Have:

• Working Mobile application for asset viewing targeted at Gen-Z age group

• Design and develop a prototype which has a high customer experience design and HCI.

Nice To Have:

• Fully working backend is not a requirement. Application can have a static data to power the application.

Project Coordinator: Kumar, Ajith-A Project Mentors: Sanghavi,

Seema

TBC

Project #14

FY2024/25
Term 2

UBS - Regulatory Compliance

FinRegScanner

Banks have to adhere to multiple market and exchange related financial regulations. The compliance function has to be vigilant in identifying the regulations that are published by various countries, regions and by industry bodies and implement them on time. If a bank is not regulatory compliant, that could lead to various repercussions from financial penalties, reputational impact to even posing a risk to the financial system as a whole.

Once a regulation is identified, few companies look out for vendor solutions and few companies build solutions in-house and this often requires a lot of coordination among various functions/teams to ensure that the regulation gets adhered to on time.

Hence, it would great if technology can help to assist and simplify the regulatory project management and implementation.

Right from identification of a financial regulation that the bank needs to adhere to, till the implementation, is very complex to manage, time intensive and costly affair.

Build a solution that can act as an assistive tool to Compliance function of an organization to help detect, plan and manage regulatory impacts in a timely manner within the organization.

Project Inputs:

• Project Sponsors will provide information about regulatory data sources and will also give a brief overview of Financial Regulatory Landscape and relevant support wherever required

• Project Sponsors will review the output at regular intervals to provide feedback and to refine requirements

Project Deliverables:

Must Have:

1) Identify upcoming regs and their regulatory deadline

2) Summarize the requirements for each impacted business division and able to query the regulatory text and get answers

3) Apply a chatbot feature to query the QnA

4) Provide a dashboard to visualize the key features of the regulations.

Nice To Have:

1) Build a machine learning model to classify the regulation, identify the potential impacts for each business division

2) Provide a comparison with other regulations of similar nature

Project Coordinator: Kumar, Ajith-A

Project Mentors: Kumar, Phanindra; Kumar, Ajith-A

TBC

Project #15

FY2024/25
Term 2

UBS - Wealth Management

Gamified Financial Literacy Application

Financial Literacy is essential in wealth management as it enables individuals to make informed decisions about growing, protecting and preserving their assets.

The ask is to create a gamified financial literacy app that teaches essential money management skills through interactive challenges, quizzes, activities, simulations and make financial education engaging and fun for all ages. Users earn badges and unlock new levels as they progress through next stages in their learning paths consisting of topics ranging from time value of money, insurance, emergency fund, asset allocation, budgeting, saving, investing etc.

Financial Literacy is essential in wealth management as it enables individuals to make informed decisions about growing, protecting and preserving their assets.

The ask is to create a gamified financial literacy app that teaches essential money management skills through interactive challenges, quizzes, activities, simulations and make financial education engaging and fun for all ages. Users earn badges and unlock new levels as they progress through next stages in their learning paths consisting of topics ranging from time value of money, insurance, emergency fund, asset allocation, budgeting, saving, investing etc.

Project Inputs:

• Project sponsors will share sufficient information regarding the various aspects of personal finance

• Mentors will guide the students on building learning paths and scenario simulations

• Mentors will review the progress at regular intervals to refine requirements and usability of the app.

Project Deliverables:

Must Have:

• Fully functional responsive / mobile native application with at least 2-3 financial literacy learning paths.

• Excellent user experience with security features implemented.

• Real time analytics to track progress with personalized insights and badges

• Admin dashboard showing the learning progress, and the badges earned by all the users.

Nice To Have:

• Integration with ChatGPT or other LLMs for personal finance scenario simulations

Project Coordinator: Kumar, Ajith-A

Project Mentors: Gopalan Ramakrishnan

TBC

Archived Projects (no longer available)

Item	Project Sponsor	Project Description	Project Deliverables	Project Stakeholders
FY2024/25 Term 1	UBS	(Not Selected) News Screener for Relevant Investment Opportunities - Bankers and Investment counselors (ICs) develop deep relationships with clients and provide them with relevant investment and opportunities advice based on client’s needs. Given the current volatile world and lots of information being generated every moment, analysts require smart intelligent tools to sort through all those and provide clients with relevant investment advice in a timely manner. The ask is to develop a tool to scan news, digest and provide news in categories like sector, region and entity, and to provide relevant sentiment of the news.	Students are expected to deliver a system that includes the following: Working dashboard that provides a real view of relevant sectors and entities. View provides contextual correlated sentiment assessment of entities. View provides trigger notifications when significant activity threshold is breached (optional). View provides collected historical information and perform system end to end risk and returns on entities. Ability to collect data from different sources. Students are free to use any visualization & analysis tools, generative AI, APIs and technology of the team’s choice. However, the solution should be hosted in an Azure Cloud. Project sponsors will provide 5 public names, and suggested data sources on which the output should be created. We will review at regular intervals the outputs to refine requirements and usability of output. We will provide support on how to perform identity matching.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Hossain, Mohammad-Jahangir email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	UBS	Smart Portfolio Optimizer - A portfolio manager is a person or group of people responsible for investing a mutual, exchange traded or closed-end fund's assets, implementing its investment strategy, and managing day-to-day portfolio trading. Portfolio management can be active or passive, and historical performance records indicate that only a minority of active fund managers consistently beat the market. The ask is to build an intelligent system capable of recommending instruments based on risk tolerance levels and target expected returns, constructing portfolios based on the strategy, and generating orders when there is a change in strategy or cashflow.	Students are expected to deliver a system that includes the following: A working and intuitive UI with the ability to create, update, and review portfolios. The UI should show suggestions and red flags with the source of information. Ability to generate and review orders. Portfolio UI to show working orders and positions (with real-time updates from backend data feed). A dashboard to display analytics to show the portfolio performance. Project sponsors will share sufficient context so students can understand how Asset Management functions. Mentors will guide students on portfolio construction and constraints to be applied and will provide sample instrument details.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Avula Chandra Shekar, Mayur Nagthane and Mani Kavandampatty email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	UBS	(Not Selected) Client News Screener - IBankers and Investment counselors (ICs) develop deep relationships with clients to understand and better serve their needs. Client Advisors today must manually search through publicly available news sources to both find public appearances or news about their clients to ensure they better understand the background of the client, and recent activity that may indicate investment preferences. The ask is to create a tool that scans publicly available social media and news sources for news about clients and recent posts/views of clients.	Students are expected to deliver the following: Web application that can summarize publicly available social media and news sources for news about clients and recent posts/views of clients. Excellent user experience. Machine learning model that can do the identity matching. Students are free to use any visualization & analysis tools, generative AI, APIs and technology of the team’s choice. However, the solution should be hosted in an Azure Cloud. Project sponsors will provide 5 public names, and suggested data sources on which the output should be created. We will review at regular intervals the outputs to refine requirements and usability of output. We will provide support on how to perform identity matching.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Seema Sanghavi email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	OCBC	(Not Selected) Intragroup Payments using Digital Tokens - Payments between the customers of OCBC Group (OCBC Singapore to OCBC Hongkong) entities involve FX booking, Cash Transfer, Settlement and Reconciliation. Usually, it takes a day for the beneficiary to receive funds into their account and needs settlement through Nostro-Vostro accounts. This project is to develop a near realtime cross-border clearing and settlement solution for intra group corporate payments using blockchain technology.	Students are expected to deliver the following: Working prototype of digital token transfers. Measurable proof that cross-border intragroup corporate payments can be cleared and settled in near realtime using DLT. Project sponsors will share sufficient context so students can understand how the Digital Token Transfers & DLT together can speed up payments (within select OCBC group entities). Students may use the existing OCBC Blockchain platform & Payment Engine to execute digital token transfers.	Project Coordinator: Lim Dedy Daryono limdd@ocbc.com Project Mentor: Paladugu Narendra Kumar (Naren) email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	OCBC	Blockchain Applications (Zero Knowledge Proofs) - Banks rely heavily on transaction auditing to ensure compliance, detect fraud, and maintain the integrity of their financial records. However, traditional auditing methods often involve sharing sensitive transaction details, compromising the privacy and security of customers' financial information. In this project, we will dive into zero knowledge proofs, a revolutionary concept in the field of cryptography and privacy. Zero knowledge proofs are a mathematical technique that allows one party, called the prover, to convince another party, called the verifier, that a certain statement is true without revealing any additional information about the statement itself. This project aims to utilize Zero Knowledge Proofs in the enhancement of data privacy and protection of the Bank’s customers. Such Zero Knowledge Proofs are intended to be used / integrated alongside the Bank’s blockchain technology stack, such as smart contracts and microservices.	Students are expected to deliver the following: A review of existing literature, including academic papers, case studies, and real-world implementations of zero knowledge proofs. An analysis of the strengths and weaknesses, underlying mathematics, and algorithms behind zero knowledge proofs. Identification of potential challenges or security concerns and proposed strategies to address them. A proof-of-concept prototype based on secure and efficient transaction auditing using Zero Knowledge Proofs. Project sponsors will share sufficient context so students can understand its use cases, discussing the benefits and limitations of implementing zero knowledge proofs and how it can benefit end users. The project details, explanation of the zero knowledge proof applications and other useful details will be shared.	Project Coordinator: Ravindra Kumar ravindrakumar@ocbc.com Project Mentor: Jorden Seet email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	UOB Kay Hian	Data Analytics Hub - The brokerage currently faces challenges in effectively analyzing the extensive data gathered from various sources. This leads to wastage of resources as they have the potential to create value for the company. The primary objective of this project is to develop a comprehensive data analytics module that acts as the central hub for analyzing data related to the brokerage's online webinars and marketing activities. The module aims to provide actionable insights that enhance the effectiveness of events, webinars, and marketing initiatives. The target audience for this project includes internal stakeholders within the organization who are involved in planning, executing, and evaluating events, webinars, and marketing campaigns.	Students are expected to deliver a system that includes the following: A data analytics hub capable of generating actionable insights, not limited to just for the organization's events, webinars, and marketing activities. Implementation of a versatile system that can seamlessly integrate with different data sources including CRM systems, social media platforms, and email marketing tools. Generation of KPI analysis reports on a monthly, quarterly, and annual basis. Gather and track feedback from various engagement activities. Automate event registration processes, streamlining attendee registration, confirmation, and communication, and integrations with the data hub for comprehensive analysis. Project sponsors will provide context to help understand the significance and value of the data analytics hub including detailed insights into current workflows and processes, and information about platforms and types of data collected, facilitating seamless data integration and analysis.	Project Coordinator: Venice Kong Min Li venicekong@uobkayhian.com Project Mentor: Charles Ng Guiquan charlesng@uobkayhian.com Project Supervisor: TBD email TBD
FY2024/25 Term 1	UOB Kay Hian	(Not Selected) Rewards Club - The reliance on outdated manual rewards points systems in our brokerage platform hampers efficiency and fails to meet modern investor demands, hindering competitiveness. This inefficiency not only impacts the productivity of trading representatives but also affects the user experience for clients. The project aims to automate the workflow of the existing rewards system, addressing the inefficiencies of the current manual process. It involves the development of a system that streamlines redemption activities and enhances user experience through a UI/UX revamp. Additionally, the new system will include features such as an audit log of transactions, a management information system (MIS), and a live dashboard for real-time monitoring.	Students are expected to deliver a system that includes the following: Automated rewards points system for both the company and the client. Scalability for potential integration into a separate ongoing mobile project. An intuitive platform for clients to easily earn, monitor, and utilize points. A dashboard for tracking the redemption of various rewards, including analytics on which rewards are redeemed the most, user preferences, and trends over time. Reporting features to provide insights into the effectiveness of the rewards points system, including metrics such as client engagement, redemption rates, and ROI. Project sponsors will share sufficient context so students can understand how/where this dashboard brings value to users including detailed information about our current rewards program, user feedback and suggestions for UI/UX revamp, access to relevant data and resources for integration, any regulatory guidelines and compliance requirements.	Project Coordinator: Alvin Cheong Yi Wei alvincheong@uobkayhian.com Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	Tiger Fund Management	AI Prediction for Asset Allocation - Tiger Fund Management is a fund management company that provides investment solutions including discretionary portfolio management products. We are the sister company of Tiger Brokers. Tiger Brokers is the leading online broker in Singapore, having disrupted the industry with zero commission in the past three years. Portfolio managers struggle with real-time risk assessments for dynamic markets, hindering optimal asset allocation and portfolio optimization. Given that Artificial Intelligence excels in big data, predictive analytics could enhance investment edge by integrating diverse data from sentiment, economics, fundamental, and technical indicators.	Students are expected to deliver a system that includes the following: An AI/Machine Learning model for a dynamic Risk Appetite Indicator (0-10) to guide asset allocation into major asset classes such as equities, bonds, and commodities. The AI model should be capable of continuous learning and adjusting its predictions to evolving sentiment, economics, fundamental, and technical data. Data could be web-scrapped from sources such as FRED (Federal Reserve Economic Data), World Bank, and Yahoo Finance. Incorporate sentiment analysis from news, social media, and financial reports to objectively feed the Risk Appetite Indicator. An intuitive user interface which exposes the underlying AI model and provides actionable insights into asset allocation.	Project Coordinator: Edmund Chan edmund.chan@tigerfund.com.sg Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	Tiger Fund Management	(Not Selected) AI Prediction for Sector Allocation - Tiger Fund Management is a fund management company that provides investment solutions including discretionary portfolio management products. We are the sister company of Tiger Brokers. Tiger Brokers is the leading online broker in Singapore, having disrupted the industry with zero commission in the past three years. Portfolio managers struggle with real-time risk assessments for dynamic markets, hindering optimal sector allocation and portfolio optimization. Given that Artificial Intelligence excels in big data, predictive analytics could enhance investment edge by integrating diverse data from sentiment, economics, fundamental, and technical indicators.	Students are expected to deliver a system that includes the following: An AI/Machine Learning model for a dynamic Risk Appetite Indicator (0-10) to guide sector allocation into various GICS sectors such as Information Technology, Energy, Financials, etc. The AI model should be capable of continuous learning and adjusting its predictions to evolving sentiment, economics, fundamental, and technical data. Data could be web-scrapped from sources such as FRED (Federal Reserve Economic Data), World Bank, and Yahoo Finance. Incorporate sentiment analysis from news, social media, and financial reports to objectively feed the Risk Appetite Indicator. An intuitive user interface which exposes the underlying AI model and provides actionable insights into sector allocation.	Project Coordinator: Edmund Chan edmund.chan@tigerfund.com.sg Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2024/25 Term 1	SMU / Narwhal Financial Systems	Corporate Internet Banking - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. We have reached the maximum capacity on the current SMU tBank infrastructure, and the performance of the system is degrading which affects student lab exercises. A previous IS484 team has already migrated the SMU tBank backend services from TIBCO BusinessWorks (hosted on AWS) to OutSystems low code application platform. OutSystems is a much more robust and scalable technology platform. This project is to migrate the current SMU tBank Corporate Internet Banking frontend UI from Vue.js to OutSystems. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to migrate (re-develop) the current SMU tBank Corporate Internet Banking frontend UI from Vue.js to OutSystems, including the following components: Existing features: (to be migrated) Dashboard view of customer accounts and statistics. Drill down view of deposit and loan accounts. Fund transfers: setup beneficiaries, transfer funds, bill payments, setup standing instructions. Setup notification preferences, balance/transaction trigger alerts. Payments – upload payment instructions for interbank clearing and settlement. New features: Upload corporate financial statements, extract financials using NLP models. Generate credit score based on financial ratios. Apply for corporate loans. Manage existing loans, e.g., partial/full loan repayments. Setup schedule and rules for cash concentration. Trade Finance – Letter of Credit, Bill of Lading, Bill of Exchange, Factoring/Bill Discounting. A previous IS484 team has already migrated the required SMU tBank backend services to OutSystems. All the API documentation will be provided.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: TBD email
FY2024/25 Term 1	SMU / Narwhal Financial Systems	(Not Selected) Automated Clearing House - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. We have reached the maximum capacity on the current SMU tBank infrastructure, and the performance of the system is degrading which affects student lab exercises. A previous IS484 team has already migrated the SMU tBank backend services from TIBCO BusinessWorks (hosted on AWS) to OutSystems low code application platform. OutSystems is a much more robust and scalable technology platform. This project is to migrate the current SMU tBank Automated Clearing House frontend UI from vanilla javascript to OutSystems. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to migrate (re-develop) the current SMU tBank Automated Clearing House frontend UI from vanilla javascript to OutSystems, including the following components: Register new bank. Edit existing bank details. Manage settlement rules for a bank, and illiquidity cases which trigger them. View the status of a given payment. Setup settlement schedule, and fees, for a bank. Invoke settlement on demand. View settlement account with central bank. Reports – Bank Report, Clearing House Revenue Report, Exception Report A previous IS484 team has already migrated the required SMU tBank backend services to OutSystems. All the API documentation will be provided.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: TBD email
FY2023/24 Term 2	UBS	Client News Screening - Bankers and Investment Counsellors develop deep relationships with clients to understand and better serve their needs. Client Advisors today must manually search through publicly available news sources to find public appearances or news about their clients, to ensure they better understand the background of the client and their activity that may indicate investment preferences. The ask is to create a tool that scans publicly available information about clients and provides a summary view of the information for Client Advisors.	Students are expected to deliver a tool that does the following: Scans publicly available social media and news sources for news about clients and recent posts/views of clients. Summarizes these views into a digestible format for Client Advisors. Ensures each data point has a source link, that would enable the Client Advisor to verify that the subject is indeed their client. Students are free to use any visualization & analysis tools, generative AI, APIs and technology of the team’s choice. However, the solution should be hosted in an Azure Cloud. Project sponsors will provide 5 public names, and suggested data sources on which the output should be created. We will review at regular intervals the outputs to refine requirements and usability of output. We will provide support on how to perform identity matching.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Tim Way email TBD Project Supervisor: Dennis Ng dennisng@smu.edu.sg
FY2023/24 Term 2	UBS	(Project cancelled by UBS) Conversation Data Analytics - Bankers and Investment Counsellors develop deep relationships with clients to understand and better serve their needs. Client Advisors must take notes of conversations, and record actions. This takes time and they can forget things, when they do, client s suffer a suboptimal service. The ask is to create a tool that transcribes audio conversations into text and provides a summary of the conversation for Client Advisors.	Students are expected to deliver a tool that does the following: Turns the text from conversations into a transcript. (The conversation should be in English.) Identifies who is talking and identifies whether they are engaged in the conversation. Generates a summarized minutes of the conversion that includes the key topics that were discussed and the key actions. The minutes can then be sent to all parties. Provides a visualization that shows the engagement level (length of time talking) of all parties involved in the conversation. Students are free to use any visualization & analysis tools, generative AI, APIs and technology of the team’s choice. However, the solution should be hosted in an Azure Cloud. Project sponsors will make themselves available to be recorded in 3 conversations. We will review at regular intervals the outputs to refine requirements and usability of output.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Tim Way email TBD Project Supervisor: TBD email TBD
FY2023/24 Term 2	UBS	Mission Analyst - In technology services monitoring, knowing the status of services is mission critical. Monitoring different components using different monitoring tools it very time consuming. The ask is to create a tool that consolidates alerts from different monitoring tools into a single portal. Based on incident alerts we should be able to identify the issue quickly and know the status of our services. The objective is to reduce the effort from engineers to prepare daily status updates, and to provide management with a consolidated view of status of all applications.	Students are expected to deliver a tool that does the following: Analyses different monitoring tools of infra / middleware / applications and consolidates information based on location, severity, and service status. Provide a high-level view of mission critical services. Provide a drill down view on any incident under management. Provide notifications on incident occurrences based on location and severity.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Raj Vedachalam email TBD Project Supervisor: Mahesh Goel maheshgoel@smu.edu.sg
FY2023/24 Term 2	OCBC	(Project deferred) Intragroup Payments using Digital Tokens - Payments between the customers of OCBC Group (OCBC Singapore to OCBC Hongkong) entities involve FX booking, Cash Transfer, Settlement and Reconciliation. Usually, it takes a day for the beneficiary to receive funds into their account and needs settlement through Nostro-Vostro accounts. This project is to develop a near realtime cross-border clearing and settlement solution for intra group corporate payments using blockchain technology.	Students are expected to deliver the following: Working prototype of digital token transfers. Measurable proof that cross-border intragroup corporate payments can be cleared and settled in near realtime using DLT. Project sponsors will share sufficient context so students can understand how the Digital Token Transfers & DLT together can speed up payments (within select OCBC group entities). Students may use the existing OCBC Blockchain platform & Payment Engine to execute digital token transfers.	Project Coordinator: Lim Dedy Daryono limdd@ocbc.com Project Mentor: Paladugu Narendra Kumar (Naren) email TBD Project Supervisor: TBD email TBD
FY2023/24 Term 2	OCBC	(Project deferred) Blockchain Applications (Zero Knowledge Proofs) - Banks rely heavily on transaction auditing to ensure compliance, detect fraud, and maintain the integrity of their financial records. However, traditional auditing methods often involve sharing sensitive transaction details, compromising the privacy and security of customers' financial information. In this project, we will dive into zero knowledge proofs, a revolutionary concept in the field of cryptography and privacy. Zero knowledge proofs are a mathematical technique that allows one party, called the prover, to convince another party, called the verifier, that a certain statement is true without revealing any additional information about the statement itself. This project aims to utilize Zero Knowledge Proofs in the enhancement of data privacy and protection of the Bank’s customers. Such Zero Knowledge Proofs are intended to be used / integrated alongside the Bank’s blockchain technology stack, such as smart contracts and microservices.	Students are expected to deliver the following: A review of existing literature, including academic papers, case studies, and real-world implementations of zero knowledge proofs. An analysis of the strengths and weaknesses, underlying mathematics, and algorithms behind zero knowledge proofs. Identification of potential challenges or security concerns and proposed strategies to address them. A proof-of-concept prototype based on secure and efficient transaction auditing using Zero Knowledge Proofs. Project sponsors will share sufficient context so students can understand its use cases, discussing the benefits and limitations of implementing zero knowledge proofs and how it can benefit end users. The project details, explanation of the zero knowledge proof applications and other useful details will be shared.	Project Coordinator: Ravindra Kumar ravindrakumar@ocbc.com Project Mentor: Jorden Seet email TBD Project Supervisor: TBD email TBD
FY2023/24 Term 2	Vertex Holdings	Chatbot for Venture Capital - The project involves developing a chatbot tailored for venture capitalists (VCs). The chatbot should be designed to gather, process, and deliver relevant information from various sources e.g., Pitchbook, Crunchbase to help investment Managers stay informed about the emerging startups, latest market trends, and sector-specific insights. By leveraging large language models, prompt engineering and other techniques, the chatbot will provide personalized updates and recommendations, enabling investment managers to make more informed investment decisions efficiently.	Students are expected to deliver the following: Chatbot Interface: Develop an intuitive and user-friendly chatbot interface that VCs can interact with easily. Data Integration: Integrate the chatbot with diverse data sources, including news articles, social media feeds, startup databases, industry reports, and financial data. Implement data retrieval mechanisms that ensure the chatbot gathers the most current and relevant information. Integration: Integrate the GPT-3.5 language model into the chatbot's framework, leveraging its natural language understanding and generation capabilities to facilitate meaningful interactions with VCs. Also consider using Langchain and Prompt Engineering. Project sponsor will provide sufficient context so students can understand how this chatbot brings value to users. We will provide relevant databases, APIs, and expected chatbot interface design.	Project Coordinator: Joey Chua email TBD Project Mentor: Xiao Dong email TBD Project Supervisor: Dennis Ng dennisng@smu.edu.sg
FY2023/24 Term 2	Vertex Holdings	Pitchdecks to Investment Memos - The "Deck2Memo" Conversion Project aims to develop an advanced solution utilizing Large Language Models (LLMs) to automate the conversion of pitch decks into investment memos. By harnessing the capabilities of LLMs, such as GPT-3.5, this project will significantly streamline the process of distilling essential information from pitch decks and generating comprehensive investment memos, enabling faster decision-making and enhanced communication within the investment process.	Students are expected to deliver the following: Pitch Deck Analysis: Develop a module that ingests pitch deck files in various formats (PDF, PowerPoint, etc.), using Optical Character Recognition (OCR) and text extraction techniques. Text Summarization: Implement LLM-based text summarization algorithms to condense the key points and content of the pitch deck, e.g., company details, value proposition, market positioning, financial projections, and team background. Investment Memo Generation: Generate comprehensive investment memos which include company overview, market analysis, competitive landscape, growth potential, risks, financial projections, and investment rationale. Customization and Formatting: Design a user-friendly interface that allows users to customize the generated investment memos. Users should be able to edit and format sections, add additional insights, and include their own commentary. Project sponsor will provide sufficient context so students can understand how this project brings value to users. We will provide sample Pitchdeks and expected investment memos to be generated.	Project Coordinator: Joey Chua email TBD Project Mentor: Xiao Dong email TBD Project Supervisor: Dennis Ng dennisng@smu.edu.sg
FY2023/24 Term 2	Vertex Holdings	Portfolio Marketplace - The project entails creating a comprehensive marketplace platform specifically designed for a venture capital to showcase their portfolio companies to potential clients, investors, and partners. The platform will not only serve as a showcase but also incorporate AI-driven recommendation features to suggest relevant portfolio companies to visitors based on their industry and interests. This dynamic platform will enhance the visibility of portfolio companies and foster meaningful connections within the startup ecosystem.	Students are expected to deliver the following: Portfolio Company Profiles: Develop profiles for each portfolio company including industry, product/service offerings, market traction, team, and notable achievements. AI-Powered Recommendation Engine: Implement a recommendation engine that analyzes user profiles and preferences to suggest relevant portfolio companies, considering industry expertise, market trends, and potential synergies. Dynamic User Profiles: Create user profiles that capture the interests, industry focus, and investment criteria of visitors. Allow users to customize their own profiles and preferences. Advanced Search Functionality: Build a robust search feature that enables users to search for portfolio companies based on specific criteria, such as industry, location, funding stage, and technology focus. Networking Opportunities: Include networking features that enable visitors to connect directly with portfolio company representatives. This could involve messaging and scheduling meetings. Project sponsor will provide sufficient context so students can understand how this project brings value to users. We will provide a sample list of portfolio companies along with the companies' description and industries, and the expected user interface design.	Project Coordinator: Joey Chua email TBD Project Mentor: Xiao Dong email TBD Project Supervisor: Dennis Ng dennisng@smu.edu.sg
FY2023/24 Term 2	SMU / Narwhal Financial Systems	Branch Teller - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. We have reached the maximum capacity on the current SMU tBank infrastructure, and the performance of the system is degrading which affects student lab exercises. A previous IS484 team has already migrated the SMU tBank backend services from TIBCO BusinessWorks (hosted on AWS) to OutSystems low code application platform. OutSystems is a much more robust and scalable technology platform. This project is to migrate the current SMU tBank Branch Teller frontend UI from Vue.js to OutSystems. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to migrate (re-develop) the current SMU tBank Branch Teller frontend UI from Vue.js to OutSystems, including the following components: Create new retail/corporate customers. Edit existing customer details. Dashboard view of customer accounts and statistics. Create customer deposit accounts, e.g., CASA, Term Deposit Create customer loan accounts for both retail and corporate customers. Execute transactions: deposits/withdrawals, bill payments, loan repayments. View transaction history. Setup direct debit authorizations. Credit approval simulator. View reference data, e.g., transaction codes, product parameters. A previous IS484 team has already migrated the required SMU tBank backend services to OutSystems. All the API documentation will be provided.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: Mahesh Goel maheshgoel@smu.edu.sg
FY2023/24 Term 2	SMU / Narwhal Financial Systems	Retail Internet Banking - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. We have reached the maximum capacity on the current SMU tBank infrastructure, and the performance of the system is degrading which affects student lab exercises. A previous IS484 team has already migrated the SMU tBank backend services from TIBCO BusinessWorks (hosted on AWS) to OutSystems low code application platform. OutSystems is a much more robust and scalable technology platform. This project is to migrate the current SMU tBank Retail Internet Banking frontend UI from Vue.js to OutSystems. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to migrate (re-develop) the current SMU tBank Internet Banking frontend UI from Vue.js to OutSystems, including the following components: Dashboard view of customer accounts and statistics. Drill down view of deposit and loan accounts. Fund transfers: setup beneficiaries, transfer to own/other account, bill payments. Setup standing instructions and GIRO (direct debit) arrangements. Apply for retail loans. Manage existing loans, e.g., partial/full loan repayments. Wealth management products: dual currency deposits, stock management, FX forward contracts. Book appointments with bank relationship managers. Update personal profile, reset PIN. Setup notification preferences, balance/transaction trigger alerts. Setup affinities (interests), opt into marketing messages. A previous IS484 team has already migrated the required SMU tBank backend services to OutSystems. All the API documentation will be provided.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: Dennis Ng dennisng@smu.edu.sg
FY2023/24 Term 2	UBS	(Project deferred) Modern Web/Mobile App for Portfolio Viewing - There are already a quite a lot of Banking asset viewing and portfolio viewing apps in the market currently. Having a great user experience for such apps are key for success of any business. User experience is garnered from Customer experience strategy, research, and design. Understanding user behavior and human computer interaction techniques are key in designing and implementing the next gen user experience application.	Students are expected to deliver the following: Native IOS/android mobile application and web application using the latest technology which inculcates great customer experience design. User experience design and wireframes. The backend may have mock data to begin with. Key success criteria are to have a great visual and customer experience for these apps.	Project Coordinator: Ajith Kumar ajith-a.kumar@ubs.com Project Mentor: Ajith Kumar ajith-a.kumar@ubs.com Project Supervisor: TBD email TBD
FY2023/24 Term 1	OCBC	(Not Selected) Blockchain Applications - Currently there is bank wide initiative to leverage on the innovative use of NFTs to capture employee profile and personal traits as staff avatars and issuance of OCBC collectibles for commemorative special occasions. To support these initiatives, there is a need to develop a NFT exchange that comes with block-explorer functionality to verify smart contract details (such as ownership, time deployed etc.) and to call smart contract functions. It will also support only barter trade (i.e. without tokens or cash payments).	Students are expected to deliver a prototype as follows: A prototype of an NFT exchange with block-explorer functionality. Block-explorer is able to verify smart-contract details (such as ownership, time deployed etc.). Block-explorer is able to call smart-contract functions. UI/UX interface to allow barter trade. Project sponsors will share sufficient context so students can understand how and where the NFT application can benefit the end users. The sample documents, explanation of the NFT applications and other useful details will be shared.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Neo Wei Cheong email TBD Project Supervisor: TBD email TBD
FY2023/24 Term 1	OCBC	Low Code No Code Applications - A low-code development platform (LCDP) provides a rapid prototyping environment used to create software applications through a graphical user interface. A low-coded platform may produce entirely operational applications or require additional coding for specific situations. We propose to develop Data APIs and microservices using Low code technology automation to deliver easy access to our data (reference / product / transactional) for interfacing to our Web, Mobile UI and reposting modules. This promotes an agile way of software development.	Students are expected to deliver a prototype as follows: Proof of concept for Low Code products. Design new APIs and microservices based of selection made by project sponsor. Working APIs and microservices for data from current sources. Project sponsors will share sufficient context so students can understand how current data flow works and what we expect from the APIs. Details about Low code products which can be used by students will be shared.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Neo Wei Cheong email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	OCBC	Next Generation Mobile App - The current mobile application is relying on pull mechanism (restful calls) to get customer product portfolio and balances. If a customer does transactions offline (pay via credit/debit card or ATM withdrawal etc.) or if there are any offers generated in realtime then customer needs to either logout and login or the mobile app needs to refresh at certain intervals via server call to check for updates which create additional network traffic. The objective of this project is to develop an enhanced mobile application to provide realtime auto refresh and contextual offers to customers.	Students are expected to deliver a prototype as follows: Mobile application which supports streaming. When customer does debit card payment or ATM transaction then balance should get auto updated in app. Instead of App call servers at interval to check update use streaming service where server send mobile client updates. Build a microservices based offer engine. This engine will monitor customer transactions (debit, credit, new products etc.) and based on rules matrix provide relevant offers and products to customer. e.g., engine detect that customer bought a fight ticket and offer travel insurance to customer. Offers generated in realtime are sent to customers and made available in in app mailbox pre and post login.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Akhil Baheti email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	UBS	Client Experience Index - We are creating a unified client experience index that reflects the level of experience at a task level for our digital offerings. The idea is to have this as a standard across different services on the digital platform so that we can compare improvements or even experience levels between different tasks in different digital channels. The aim of the project is to develop an algorithm that takes inputs from a knowledge base data base (Graph DB) to output a quantitative measure of the experience. We will still show a couple of sub ratings which makes the number more explainable, but this is also part of the algorithm.	Students are expected to deliver the following: Algorithm that calculates (statistically and using AI techniques) a simplified measure of client experience. A demonstration of how the calculations work and a good UI presentation of the index with drill down capabilities. Project sponsors will share sufficient context so students can understand how/where this dashboard brings value to users. We will provide non sensitive data that will help students create their own mock data set and run the algorithm to come up with measures.	Project Coordinator: Saju Phillip saju.philip@ubs.com Project Mentor: Kai Xian email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	UBS	In-App Feedback Solution - The ability to capture client feedback and satisfaction scores are vital to understand how customers feel about the digital services and most often this is a least priority in traditional app development. The scenario is changing fast and today clients are willing to pay higher price for a good experience in any industry. The private bank is focusing on rich clients, and they are more than willing to pay for a premium offering and willing to spend extra for that. Capturing client feedback, SUS, CSAT and other industry standard measures by a traditional survey may impact the overall experience but developing a psychometric or other gamifying methods to capture what matters at the right time is important to improve digital products. The aim of this project is to research, identify and implement a seamless feedback capture solution for digital services.	Students are expected to deliver the following: Working code that can be plugged in to applications to record client feedback. Prototype application to demonstrate the functionality. Architectural blueprint and deployment diagrams. Project sponsors will share sufficient context so students can understand how they can design a component that can be called from any app to capture the specific feedback.. Project sponsors will guide on technical framework and process to capture and record the feedback in a structured way.	Project Coordinator: Saju Phillip saju.philip@ubs.com Project Mentor: Kai Xian email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	UBS	Insights Classification Engine - Currently there are various sources of feedback in unstructured form from internal and external sources and we want to build a system that can use the latest AI models to classify the comments / feedback in UBS topology, summarize and rank them for feeding an internal dashboard on client insights. The aim of this projects is to build a Rules Engine based on AI (Including GPT) that will: Perform unstructured data classification. Summarization of similar statements. Ranking of key statements / insights.	Students are expected to deliver a solution that will accomplish the following: Download the reviews in plain text form from sources listed by UBS. An opensource AI model (Large language model) or BERT model that can classify the statements based on UBS ontology. A summarization engine using latest techniques. Ranking algorithm to bring out the key insights in each category which can be fed into a dashboard. Project sponsors will share sufficient context so students can understand the UBS ontology. Students can use publicly available comments on UBS products like app store and play store reviews in addition to mock data that can be created from other banks reviews or product reviews.	Project Coordinator: Saju Phillip saju.philip@ubs.com Project Mentor: Vilva M email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	UBS	Design Ops Pipeline - UBS is focusing on building better client experiences and Design Thinking and Design Ops are two key tools/methods we plan to adopt for this. We use Dev Ops in software development to move the concept to use case, code and a feature in an application with most of the stages/gates automated like automated testing, repository integration, and version and change control. The aim of this project is to apply Dev Ops concepts to Design, where the artifacts involved are Ideas, Rough sketches, Prototypes hosted, their versions, validation inputs by business, High Fidelity and Low fidelity wireframes, Visual assets, Design system components, Client feedback comments, and pain points identified for continuous improvement to name a few. There will be extensive file management & versioning with File Operations along with Idea/Feature/Feedback lifecycle management to build a Design Ops pipeline.	Students are expected to deliver the following: A process diagram/ 8design to show the tools, actor and the input/output for main activities in a design function of a corporate. Exposing APIs if available with standard tools or integrating the artifacts into a well-defined file management structure. Managing requirements and feedback from clients and business about the features/artifacts using automation across its lifecycle. A final demonstrate-able solution that will show how an idea will move through the design Ops pipeline in a seamless way for presentation. We expect to use standard tools like Axure, Figma, Jira, Teams and other tools with Python scripts/automation to build this end-to-end pipeline.	Project Coordinator: Saju Phillip saju.philip@ubs.com Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	SMU / Narwhal Financial Systems	Core Banking System Migration - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. The current SMU tBank backend services are developed using TIBCO BusinessWorks hosted on an AWS Windows EC2 instance. We have reached the maximum capacity on the current Window EC2 configuration, and the performance of the system is degrading which affects student lab exercises. This project is to migrate the current SMU tBank backend from Windows-based TIBCO BusinessWorks services to OutSystems low code application platform. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to complete the following tasks: Understand the current TIBCO BusinessWorks services, which requires installing the TIBCO development studio. Replicate (migrate) the functionality of the 100+ TIBCO services onto SMU's licensed OutSystems environment. Migrate the existing database over to the OutSystems environment. Develop an API Demo App (User Interface) on OutSystems to demonstrate the invocation of all 100+ services on OutSystems. Provide API documentation (Swagger).	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2023/24 Term 1	SMU / Narwhal Financial Systems	(Not Selected) Trade Finance - SMU tBank is a bespoke digital banking platform that we use to support multiple Financial Technology courses at SMU. There is a legacy Corporate Internet Banking (CIB) application that includes both Payments and Trade Finance. This legacy CIB was built on the stencils.js framework which was developed by a student. The legacy CIB is no longer in use. There is a new CIB application on vue.js but it only has Payments (used for the ACH lab in IS430 Payments). Trade Finance was never migrated over to the new CIB. This project is to replicate (migrate) the Trade Finance stencils.js code over to vue.js for the new CIB. This is to support labs in IS445 Corporate Banking. Work product from this project will also be used by Narwhal Financial Systems (NarFin), an SMU spin off company.	Students are expected to develop Trade Finance products for CIB, including the following components: Letter of Credit: full end-to-end maker-checker processes between the issuing bank, and advising bank, including document flows and payment flows. Upload of Trade Documents: Bill of Lading, Bill of Exchange, Certificate of Origin, etc.. Related Trade Finance products: Shipping Guarantee, Trust Receipt, Bill Discounting, Export Factoring, etc.. Gamification / Leaderboard for classroom usage, to enhance learning of Trade Finance products.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: TBD email
FY2022/23 Term 2	NETS	(Not Selected) Transform Internet Online Direct Debit via Web3.0 - Web 3.0 blockchain identity which offers privacy, control, openness and interoperability is a powerful catalyst to transform the usability and technology for Internet Online Direct Debit. The Web3.0 blockchain identity is a viable secure substitute for the end-user’s internet banking ID credentials and will also streamline the user experience for Internet Online Direct Debit from a Web2 to a Web3 experience. Students are asked to create a prototype which can accomplish the following: Demonstrate the registration of a Web3.0 id (blockchain id) thru the existing banking credentials via a prototype banking app. Demonstrate Web3.0 login and notification for internet direct debit payments. Demonstrate capability on use of blockchain host to substitute and support the online internet direct debit payment processing functionality which may include a blockchain smart contract to bridge Web3.0 and legacy payment processing of the banking institutions.	Students will be tasked to build a prototype which contains the following: A prototype bank app to simulate the registration of a Web3.0 id (blockchain id) thru the existing banking credentials and to be the mobile app to enable a Web3.0 login and notification for internet direct debit payments. A blockchain host to support the Web3.0 login and payment processing functionality which may include a blockchain smart contract to bridge Web3.0 and legacy payment processing of the banking institutions. A banking payment simulator host to register and demonstrate successful payment processing and reference to Web3.0 audit trail. Project sponsors will share sufficient context so students can understand the context of internet online direct debit to enable the students to design suitable solutions to overcome the problem statement. A sample high level conceptual design, explanation of this roles and responsibilities of the components and other useful details will be available.	Project Coordinator: Lee Kai Joo Germaine germainelee@nets.com.sg Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2022/23 Term 2	NETS	Interoperable QR payments using EMVCo QR - EMVCo QR implementations currently requires consumers to download and deposit funds in multiple payment apps in order to pay to the whole spectrum of EMVCo QR merchants as opposed to only needing to use their favorite payment app. EMVCo QR merchants need to sign-up, settle and reconcile with multiple payment providers as opposed to a single party. EMVCo QR labels currently need to be replaced physically when a merchant decides to ADD or REMOVE QR payment options. Students are asked to create an interoperable payment solution using EMVCo QR which can accomplish the following: Allow users to use their favorite payment apps to pay to all EMVCo QR merchants as opposed to users having to download multiple payment apps in order to pay to merchants accepting different payment apps. Allow merchants to accept payment from all payment apps and receive settlement including consolidated reporting from only one acquirer versus settlement with multiple acquirers each representing different payment app providers. Allowing a unified and streamlined QR payload which is merchant centric and do not need replacement if the merchant decide to switch acquiring relationships.	Students are expected to deliver a prototype as follows: A working eco-system prototype comprising mock\up payment apps, merchants, EMVCo QR labels, EMVCo QR switch (if applicable) and sample transaction and settlement reporting dashboards received by both consumers, merchants and the scheme. The prototype should be able to highlight and demonstrate key concepts which are key to enabling such an interoperable QR payment scheme. Project sponsors will share sufficient context so students can understand EMVCo QR and the QR payment landscape to enable the students to design suitable solutions to overcome the problem statements. A sample high level conceptual design, explanation of this roles and responsibilities of the components and other useful details will be available.	Project Coordinator: Lee Kai Joo Germaine germainelee@nets.com.sg Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	NETS	Car Park As-A-Service - Parking can be costly especially for car users/owners who need to hop across multiple car parks for work across multiple locations within to carry out their daily business or work activities. Current season parking arrangements are also inflexible and requires the car users/owners to commit a recurring fee to only one car park location. During peak hours it can also be extremely time consuming for car users/owners to queue and seek for available car park lots. Carpark as a service is a new service concept which allows a car park operator to rent physical car park spaces from real-estate property owners and to offer use of these car park spaces to subscribers of this service for a one-time or recurring fee. This allows a car park operator to provide car park services across multiple private car parks across the city without the need to own or rent a complete physical car park. This also allows car users/owners to subscribe to a contemporary digital car park service which allows them flexible membership and subscription options which can apply across all available car parks offered by the service including pre-booking, notification of availability etc.	Students are expected to deliver a prototype as follows: A prototype consumer mobile app that provides a real time view of available car park as-as-service functions, subscription and booking options. A central car park simulator with allows business model simulation leveraging machine learning/deep learning algorithms to test a variety of simulated statistics of car users/owners, preference and requirements. A car-park-as-as-service business viability assessment report using Singapore data. Project sponsors will share sufficient context so students can understand the context of the car park payment service to enable the students to design suitable solutions to overcome the problem statements. A sample high level conceptual design, explanation of this roles and responsibilities of the components and other useful details will be available. Project sponsors will provide a baseline car park ecosystem simulator which allows the students to further enhance and develop to incorporate the required use cases and data model to support the business model simulation and machine / deep learning.	Project Coordinator: Lee Kai Joo Germaine germainelee@nets.com.sg Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	Vertex Holdings	AI Augmented Analysis of Financial Statements - Processing and analyzing management reports and financial statements of start-ups, existing portfolio companies and publicly listed organizations are a critical part of making investments. These reports however are typically in semi-structured data formats, requiring human intelligence to extract and process relevant content. This project seeks to explore the possibility of leveraging machine learning and artificial intelligence to automate the extraction, processing and interpretation of structured and unstructured content from business and financial reports to augment the investment analyst.	Students are expected to deliver a prototype as follows: Identify and implement tools to read and extract structured and unstructured content from business and financial reports in different formats e.g., PDF, PPTX, Excel. Interface for reports to be uploaded by organization, and to be able to search, interact and visualize data within and across organizations. NLP on textual content to include entity extraction, sentiment, topics, summarization. Project sponsors will share sufficient context so students can understand how/where this UI brings value to users. Project team will provide samples of business and financial reports for processing.	Project Coordinator: Joey Chua joey.chua@vertexholdings.com Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	Vertex Holdings	Company Smart News Monitoring - Investment managers need to keep abreast on latest news and developments relevant to companies they have invested in order to stay on top of their game. Current news monitoring is typically company keyword based e.g., "Vertex Holdings" which only surfaces news of direct relevance to the organization. However, various news events such as those regarding competitors, industry relevant information are important for managers to be aware about. This project will involve designing and developing a module for investment managers to review, track, and read key news items that affects the companies they have or plan to invest in.	Students are expected to deliver a prototype as follows: Develop news ingestion pipelines for searching and ingesting content based on keywords of interest. Design algorithms or heuristics to identify topics and keywords for news content that are indirectly related to a company of interest. Backend ranking methodology to score relevancy of specific articles to the investment manager. Build web application and user interface that provides an interactive way for the analyst to review, interact and make sense of the content highlighted to him. Project sponsors will share sufficient context so students can understand how/where this UI brings value to users.	Project Coordinator: Joey Chua joey.chua@vertexholdings.com Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	Vertex Holdings	(Not Selected) Robo-advisory for Go-To-Market - Investment Managers not only invest in companies, but also help with the companies’ business development in different countries. However, this not only requires significant time to search for vendors/customers, but also require local knowledge of each country e.g., how businesses operates. Currently, this requires a lot of manual effort and individual knowledge to put together. We envisage an AI augmentation tool to support this task.	Students are expected to deliver a prototype as follows: Acquisition of relevant data sources e.g., customers and vendors to related portfolio companies. Collection of datasets and information to understand various industries and markets. Web application for user to input company and market fields as well as additional supporting information required. Website interface should allow user to generate report on demand e.g., export to PDF. Generation of potential leads as well as useful information sources and opportunities for entering the market as well as contacts or events to reach out to. Project sponsors will share sufficient context so students can understand how/where this UI brings value to users. Provide list of portfolio companies and the industry the companies are in.	Project Coordinator: Joey Chua joey.chua@vertexholdings.com Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2022/23 Term 2	SMU / Narwhal Financial Systems	Automated Loan Origination System - The loan origination process for traditional banks is typically long running with many process steps involving human interaction, however for digital banks these processes are automated. This project is to prototype an automated end-to-end process for retail banking loan origination, for example a mortgage loan. The Loan Origination System (LOS) is to be deployed as an SMU tBank application, which will fulfil two purposes: a) to provide hands-on lab experience in the classroom, and b) to serve as a prototype for Narwhal Financial Systems (a.k.a. Narfin) which is an SMU spin-off company. The LOS will implement a completely automated process, starting from a customer online loan application, and ending with a loan approval (or rejection), without any “bank staff” involvement.	Students are expected to deliver a prototype as follows: Extraction of document fields using OCR technology, to complete the electronic record of the loan application. Computing a credit score, using a credit scoring model (e.g., scorecardpy). Note: the credit scoring model should be exposed as a reusable API. Implement credit decisioning rules based on the computed credit score, including pricing of the loan (i.e., the offered interest rate based on the customers risk profile). User Interfaces: Customer UI – for; a) applying for the loan online and uploading documents, b) checking loan application status, and c) accepting or rejecting loan offers. Bank Staff UI – for; a) manually making credit decisions on borderline loan applications, and b) viewing the status of all loan applications using various filters. Admin UI – for; a) configuring the credit scoring model, e.g., setting limits and constraints, and b) training the model using third party datasets, e.g., from lending club.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	SMU / Narwhal Financial Systems	Stock Trading Engine - A stock order management system and stock trading engine are to be deployed as an SMU tBank application, which will fulfil two purposes: a) to provide hands-on lab experience in the classroom, and b) to serve as a prototype for Narwhal Financial Systems (a.k.a. Narfin) which is an SMU spin-off company. The main features of the prototype are to include the following: Synchronization of stock quotes form Yahoo Finance. State Machine to facilitate the easy management of all transitions between trade states. Trade Timer to trigger the expiry of associated trades (e.g., limit orders). Trade Matching Engine to match counter party trades conducted based on the order type, price, and pending volume of each trade. Trading Algorithm whereby the trader can set parameters and execute automatic trading.	Students are expected to deliver a prototype as follows: Account Management: CRUD of Accounts. Stock Management: CRUD of Stock, Synchronization with Yahoo Finance. Trade Management: CRUD of Trade, State machine, Trade timer. Trade Matching Engine: Trade matching algorithm, Logging of all activities. Trader Book Management: CRUD to the book, Portfolio analysis. Trading Algorithm: Parameters exposed to trader, Execution of auto-trading. Gamification / Leaderboard for classroom usage, to reveal the top traders for a lab session.	Project Coordinator: Alan Megargel alanmegargel@smu.edu.sg Project Mentor: TBD email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	UBS	Client Experience Data Mesh & Dashboard - Data Mesh is a strategic approach to modern data management. The main objective of Data Mesh is to evolve beyond the traditional centralized data management methods of utilizing data warehouses and data lakes. Data Mesh emphasizes on the idea of organizational agility by empowering data producers and data consumers with the accessibility to access and manage data, without the trouble of delegating to the data lake or data warehouse team. The decentralized method of Data Mesh allocates data ownership to domain-specific groups that serve, own, and manage data as a product. We plan to build a data mesh to collect and manage data related to client experience.	Students are expected to deliver a prototype as follows: Identify the key data elements that can be collected via digital channels that can be managed as a Data Mesh. Create the domains and architecture to manage this mesh. Define and build Data products that can be consumed for measurements and calculating scores. Create a dashboard of client experience scores such as: Customer Effort Score, Net Promoter Score, Customer Satisfaction Score, Task Success Rate, Error Occurrence Rate, System Usability Scale, Time-on-task. Project sponsors will share sufficient context so students can understand how/where this brings value to further enhance client experience and design.	Project Coordinator: Saju Philip saju.philip@ubs.com Project Mentor: Sweata D , Kai Xian email TBD Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	UBS	Banking Customer Portfolio Viewing - There are already a quite a lot of banking asset viewing and portfolio viewing apps in the market currently. Having a great user experience for such apps are key for the success of any business. User experience is garnered from customer experience strategy, research and design. Understanding user behavior and human computer interaction techniques are key in designing and implementing the next generation user experience application.	Students are expected to deliver a prototype as follows: A native iOS/Android mobile application and web application using the latest technology which inculcates great customer experience design. There are already great research materials on this subject, so need a both balanced academic view and already existing app view to come out with a great application to do portfolio viewing of a Banking clients assets. The backend may have mock data to begin with so its not really expected for the app to work end to end. The key success criteria are to have a great visual and customer experience for these apps.	Project Coordinator: Saju Philip saju.philip@ubs.com Project Mentor: Ajith Kumar ajith-a.kumar@ubs.com Project Supervisor: Seema CHOKSHI seemac.2020@phdgm.smu.edu.sg
FY2022/23 Term 2	OCBC	(Not Selected) Blockchain Applications - Currently there is bank wide initiative to leverage on the innovative use of NFTs to capture employee profile and personal traits as staff avatars and issuance of OCBC collectibles for commemorative special occasions. To support these initiatives, there is a need to develop a NFT exchange that comes with block-explorer functionality to verify smart contract details (such as ownership, time deployed etc.) and to call smart contract functions. It will also support only barter trade (i.e. without tokens or cash payments).	Students are expected to deliver a prototype as follows: A prototype of an NFT exchange with block-explorer functionality. Block-explorer is able to verify smart-contract details (such as ownership, time deployed etc.). Block-explorer is able to call smart-contract functions. UI/UX interface to allow barter trade. Project sponsors will share sufficient context so students can understand how and where the NFT application can benefit the end users. The sample documents, explanation of the NFT applications and other useful details will be shared.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Neo Wei Cheong email TBD Project Supervisor: TBD email TBD
FY2022/23 Term 2	OCBC	(Not Selected) Low Code No Code Applications - A low-code development platform (LCDP) provides a rapid prototyping environment used to create software applications through a graphical user interface. A low-coded platform may produce entirely operational applications or require additional coding for specific situations. We propose to develop Data APIs and microservices using Low code technology automation to deliver easy access to our data (reference / product / transactional) for interfacing to our Web, Mobile UI and reposting modules. This promotes an agile way of software development.	Students are expected to deliver a prototype as follows: Proof of concept for Low Code products. Design new APIs and microservices based of selection made by project sponsor. Working APIs and microservices for data from current sources. Project sponsors will share sufficient context so students can understand how current data flow works and what we expect from the APIs. Details about Low code products which can be used by students will be shared.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Neo Wei Cheong email TBD Project Supervisor: TBD email TBD
FY2022/23 Term 2	OCBC	(Not Selected) Next Generation Mobile App - The current mobile application is relying on pull mechanism (restful calls) to get customer product portfolio and balances. If a customer does transactions offline (pay via credit/debit card or ATM withdrawal etc.) or if there are any offers generated in realtime then customer needs to either logout and login or the mobile app needs to refresh at certain intervals via server call to check for updates which create additional network traffic. The objective of this project is to develop an enhanced mobile application to provide realtime auto refresh and contextual offers to customers.	Students are expected to deliver a prototype as follows: Mobile application which supports streaming. When customer does debit card payment or ATM transaction then balance should get auto updated in app. Instead of App call servers at interval to check update use streaming service where server send mobile client updates. Build a microservices based offer engine. This engine will monitor customer transactions (debit, credit, new products etc.) and based on rules matrix provide relevant offers and products to customer. e.g., engine detect that customer bought a fight ticket and offer travel insurance to customer. Offers generated in realtime are sent to customers and made available in in app mailbox pre and post login.	Project Coordinator: Dedy Lim limdd@ocbc.com Project Mentor: Akhil Baheti email TBD Project Supervisor: TBD email TBD
FY2022/23 Term 1	OCBC	Online Business Account Maintenance - Business Banking provides SME & Corporate customers with a broad range of Cash & Trade products and services. Through our Digital Business Banking channels, customers are able to manage cash, loans, trade finance and perform transactions in their day-to-day business. The current account maintenance form is in PDF for customers to download. Once customer fills up the form, they will email the scan copy to operations. This process takes at least a few days to complete and incurs operation overhead. The task is to digitize the online business account maintenance services: To analyze the account maintenance form in PDF Develop UI & microservices to render the form based on configuration & capture the data digitally Allow customer to authorize the submission digitally with online signature or via SingPass	UI & microservices as a dynamic online account maintenance application. UI is preferred to be developed in ReactJS & microservices developed in Java Springboot Project sponsors will share sufficient context so students can understand how/where this UI brings value to the customers. The sample pdf form, explanation of the validations and other useful details will be shared.	Project Coordinator: Lim Dedy Daryono limdd@ocbc.com Project Mentor: Kotla Mutha Ravi Tej RaviTejKotla@ocbc.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2022/23 Term 1	OCBC	Host-to-Host (H2H) Modernization - Business Banking provides SME & Corporates customer with a broad range of Cash & Trade products and services. Through our H2H integration, customers are able to integrate with their ERP/Accounting system to perform transactions with the bank. The current H2H solution is a secured file transfer channel which supports file transfers between customers and the bank over the internet. Currently there is excessive overhead in managing folder & access controls, as there are thousands of folders that need to be maintained. In addition, H2H integration is scheduled instead of event based, and this also incurs high maintenance overhead. The task is to modernize the H2H setup & maintenance: To analyze the H2H setup & challenges Propose a new design, implementation & tool if any to ease the maintenance with better access control	New H2H solutions setup for minimal operation maintenance Event trigger capabilities (instead of scheduled) H2H is preferred to be on Linux platform with Java components if any Project sponsors will share sufficient context so students can understand how/where the new H2H integration will benefit the customers.	Project Coordinator: Lim Dedy Daryono limdd@ocbc.com Project Mentor: Kochupurackal Joseph George JosephK@ocbc.com Project Supervisor: Project not assigned
FY2022/23 Term 1	OCBC	Blockchain Applications - GO&T serves as trusted partner to co-create new business capabilities, protect technology infrastructure, manage Group’s IT operations, and run regional processing hubs. Currently there is wide range of documents used by different teams in GO&T, there’s no efficient and automated method for verifying the latest version of documents, retrieval of documents and checking authenticity. This creates operational overhead for staff who rely on getting the approved documents done by other teams. On the NFT digital assets front, due to strong demand on NFT assets, there is no standardized way and repeatable process for production of NFT assets. Business users are not able to iterate fast on digital assets creation to meet demand by customers. The task is to design and develop blockchain applications for use cases such as: Document notarization & verification Production of NFT assets	New microservices for API calls to the endpoints of blockchain for document verification. New microservices for API calls to the endpoints of blockchain for production and management of NFT assets. New smart contract to store the Hash of the documents on-chain and other meta-data stored off-chain. New smart contract for NFT assets based on ERC-721 token standard stored on-chain and other NFT meta-data stored off-chain. Project sponsors will share sufficient context so students can understand how and where the blockchain applications can benefit the end users. The sample documents, explanation of the validations and other useful details will be shared.	Project Coordinator: Lim Dedy Daryono limdd@ocbc.com Project Mentor: Neo Wei Cheong WeiCheongNeo1@ocbc.com Project Supervisor: LAU Yi Meng ymlau@smu.edu.sg
FY2022/23 Term 1	Citibank	Commodities Pricing - The Commodities Pricing Platform (Atlas) is a Sales and Trader facing application that provides timely pricing across all Commodities asset classes. The user interface is mainly configuration driven and uses a highly dynamic rule engine to represent relationships between user inputs. These configurations are used as inputs to the rules engine to define products, their defaults and what data transformations should occur based on user inputs. The configuration files the pricing platform uses can span thousands of lines of JSON. Updating this JSON manually represents an operational risk. The aim of this project is to structure the update process and reduce this risk.	Students will be asked build a UI that will: Have the ability to create, delete and modify rules engine configurations Apply validation logic across the configuration to highlight inconsistencies in the rules such as loops, duplicates or conflicts. The application should provide an intuitive UI/UX, and the ability to create new pricing products without code changes. Project sponsors will share sufficient context so students can understand how/where this application brings value to users. The data will be shared and an explanation of this data structure and other useful details will be available.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Ronnie Day ronnie.day@citi.com Project Supervisor: LAU Yi Meng ymlau@smu.edu.sg
FY2022/23 Term 1	Citibank	Preventive Cross-Platform Risk Assessment (II) - An AI machine learning platform is needed to provide risk assessments of cross application health status and predictions of downtime, based on realtime access to applications through-put performance data, in order to provide an end-to-end cross platform health assessment including daily average volume vs realtime system load. Students are tasked to build a UI with a dashboard that provides a realtime view of platform health status, leveraging machine learning/ deep learning algorithms to suggest and predict potential system downtime, potential SLA breaches, and identify trigger points /bottle necks.	Students will be tasked to build a UI that will provide: Working dashboard with realtime view of platform health status. View of contextual assessment of platform status. View of trigger notifications when risk crosses threshold. View of collected historical information. Perform system end-to-end calculated risk assessment. Ability to collect data from different applications in realtime.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Ricky Ho ricky.ho@citi.com Project Supervisor: LAU Yi Meng ymlau@smu.edu.sg
FY2022/23 Term 1	Citibank	Equities Chatbot - Citi Equities trading platform receives several queries on a daily basis. The queries currently are being sent and answered through email, symphony chat, Bloomberg chat etc. and an associate’s manual efforts are required to generate a response; either running database queries to fetch results, or leveraging their product knowledge and judgement to make predictions. This project is to create an AI chatbot to automate the process and replicate the efforts of an associate replying to queries received by the Equities team. The AI chatbot is expected to interact with traders and answer their queries. The bot must be capable of: Running 24/7 to tend to all queries Generating cohesive and accurate responses to queries in real time Processing financial jargon and acronyms as input Running database queries and displaying results Making trading algorithm predictions for products selected by trader Logging all activity to be used for analysis of performance	Students will be tasked to build the following: Functional chatbot with clean UI and robust backend Chatbot must use NLP tasks such as Word sense Disambiguation, Named Entity Recognition (NEM) and Sentiment Analysis to ensure nuanced interactions Must mine text from existing datasets to enrich the bot Must employ decision making models to make trading algorithm predictions Project Inputs: Historic queries and responses Financial acronyms compilation Product to algorithm mapping Any FAQs	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Rajeshkumar Madanlal email rs97865@citi.com Project Supervisor: LAU Yi Meng ymlau@smu.edu.sg
FY2022/23 Term 1	Citibank	Data Aggregator - Reporting and Statements generation across various countries within Citi is a critical operation for client and service operations within Citi. There is a high level of data redundancy (multiple copies of the same data), manual dependency from operations users to input data, and untimely data availability. In some cases, this becomes a regulatory concern. Students executing this project will be expected to build a middleware application that is capable of extracting data points on demand from various source or upstream systems. The objective is to build a Report On Demand (ROD) framework that can serve as a self-service fully autonomous tool for operations users, to enable: Flexibility and enable users to retrieve data on-demand Centralized data aggregation management Cost-effective and timely response to ever-changing data requirements	Features of this solution to include: Ability to upload data a dictionary in a defined format – this format can be specified by the students, Ability to create data extraction templates from the available data points in the data dictionary. Once templates are created, they can be run on-demand to extract and store these data points from source systems. Note: The data sources typically are Oracle, MSSQL and No-SQL databases. This can be further extended to File store, HDFS etc. Project sponsor will share further context on the various pain points and priorities of the problem statement. Specific use will be defined and shared with the students too.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Sandeep Sharma rajeshkumar.madanlal.sharma@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2022/23 Term 1	Citibank	Enabling Efficient On-the-job Training with AI - Citi Commercial Bank (CCB) plans to hire hundreds of staff over the next three years to fast-track growth. It is crucial that new hires joining CCB are brought up to speed efficiently on company and role-specific processes and day-to-day functions. A large part of this is done through on-the-job training, where new hires learn more about the various processes, digital platforms and resources as they do their daily work. However, given the complex nature of the business (and hence its processes and systems), it is not always easy for new hires to learn on-the-job. The ask is to create on-the-job training resource(s) and platform for employees where Line Managers / L&D partners can easily: Build learning pathways for their teams on the various digital processes and systems that they would have to get familiar with as part of their on-the-job training. Upload / maintain use-case driven content for the learning pathways. Reduce manual on-the-job trainings for new hires.	Students are expected to deliver: A working prototype to collate and prioritizes training resource(s) that enables efficient and effective on-the-job learning. The solution should be easy and intuitive to use for both managers and new hires. The working prototype would demonstrate the use of natural language processing/AI and full stack development skills to build a platform that can deliver summarized and relevant information when users make specific on-the-job queries. The solution must be able to measure the success of on-the-job learning. New hires should easily be able to navigate the learning pathways such that they can self-serve and learn on their own and Search for answers to specific on-the-job queries they have on processes / systems. Project sponsor will share further context on the various pain points and priorities around onboarding and training new hires. Specific use case and target audience personas will be defined and shared with the students too.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Go Cheng Yan cg14129@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2022/23 Term 1	Citibank	Data APIs using Low Code - Lots of our data sourcing is driven from embedding SQL or Logic in Stored procedures. This makes the application logic heavily dependent on data which sometimes is not even owned by the given service. Accessing data in an easy way within a distributed platform is a big challenge. A low-code development platform (LCDP) provides a development environment used to create application software through a graphical user interface. A low-coded platform may produce entirely operational applications, or require additional coding for specific situations https://en.wikipedia.org/wiki/Low-code_development_platform The objective is to develop Data APIs using Low code technology automation. This is an agile way of software development. It will deliver easy access of our data (reference / product / transactional) to our Web, Mobile UI and reposting modules.	Students are expected to deliver: POC for Low Code products. Design new APIs based of selection made by project sponsor. Working APIs for data from current sources. Project learnings: Experience in designing / developing APIs. Learning an agile way of application development. Proof of connects with product(s) used of Low Code automation. Experience working on data complexity in a distributed system. Good idea about Capital Markets domain. Project sponsors will share sufficient context so students can understand how current data flow works and what we expect from the APIs, and details about Low code products which can be used by Citi.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Rohit Rohatgi email rohit.rohatgi@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2022/23 Term 1	NETS	(Not Selected) Transform Internet Online Direct Debit via Web3.0 - Web 3.0 blockchain identity which offers privacy, control, openness and interoperability is a powerful catalyst to transform the usability and technology for Internet Online Direct Debit. The Web3.0 blockchain identity is a viable secure substitute for the end-user’s internet banking ID credentials and will also streamline the user experience for Internet Online Direct Debit from a Web2 to a Web3 experience. Students are asked to create a prototype which can accomplish the following: Demonstrate the registration of a Web3.0 id (blockchain id) thru the existing banking credentials via a prototype banking app. Demonstrate Web3.0 login and notification for internet direct debit payments. Demonstrate capability on use of blockchain host to substitute and support the online internet direct debit payment processing functionality which may include a blockchain smart contract to bridge Web3.0 and legacy payment processing of the banking institutions.	Students will be tasked to build a prototype which contains the following: A prototype bank app to simulate the registration of a Web3.0 id (blockchain id) thru the existing banking credentials and to be the mobile app to enable a Web3.0 login and notification for internet direct debit payments. A blockchain host to support the Web3.0 login and payment processing functionality which may include a blockchain smart contract to bridge Web3.0 and legacy payment processing of the banking institutions. A banking payment simulator host to register and demonstrate successful payment processing and reference to Web3.0 audit trail. Project sponsors will share sufficient context so students can understand the context of internet online direct debit to enable the students to design suitable solutions to overcome the problem statement. A sample high level conceptual design, explanation of this roles and responsibilities of the components and other useful details will be available.	Project Coordinator: Lee Kai Joo Germaine germainelee@nets.com.sg Project Mentor: TBD email TBD Project Supervisor: TBD email TBD
FY2021/22 Term 1	Citibank	Derivative & Structured Product Performance Dashboard - Derivative & Structured products are complex and its crucial for Bankers and investment counselors to have a consistent view for how these products perform for our clients. Apart from product performance it’s important to know product lifecycle events and any risks that may be detrimental to private bank clients. This dashboard will allow visualization of such complex information in an organized and intuitive manner. Bankers and Investment counselors (ICs) act on market trends and guidance from research teams to create customized financial products for clients. These products are created to cater to a variety financial risks and client preferences.	The ask is to create an analytics dashboard that: Allows users to view cumulative financial performance of the products. Surface product performance details, including possible risks from changes in the market conditions etc. Filter and show a summary of upcoming product milestone details – such as interest payments, premiums due etc. Allow this data to be sorted and filtered to show details for one or more clients. Visualize this data using charts, tables etc. in a simple, uncluttered fashion.	Project Coordinator: Kulkarni, Kaushik kaushik.achala.kulkarni@citi.com Project Mentor: Awan, Kashif email TBD Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2021/22 Term 1	Citibank	Preventive Cross-Platform Risk Assessment - Multiple applications are constructed together to support one of the largest Custodian banking platforms. Any of the components malfunctioning will affect productivity and also lead to a breach of the market deadline. We are seeking for an AI risk monitoring and assessment tool to enhance the platform resilience to another level. AI machine learning Platform to provide risk assessment of cross application health status and prediction of downtime. To do this, they need real time access of: Application through-put performance. End-to-end application cross-platform health assessment. Daily average volume vs. real time system load.	Students will be tasked to build a UI which: Contains a dashboard that provides a real time view of platform health status. Leverages machine learning / deep learning algorithms which suggests and predicts potential system downtime, potential SLA breaches, and identifies trigger points / bottle necks. Is able to construct end-to-end flows across different platforms.	Project Coordinator: Ho, Ricky ricky.ho@citi.com Project Mentor: Balusa, Ashok email TBD Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2021/22 Term 1	Citibank	(Old name: Document Scrutiny using a Rules Engine) Document processing using Cognitive OCR - Currently the Document Scrutiny process is a manual task which requires human intervention for regulatory validations. This process is error prone and time consuming. A Rules Engine is need with these features: Perform Data Validations & Scrutiny for the received Transactions & Documents. Rules can be configured through UI & saved to the application at any point of time. A rich UI experience is needed for user friendly & easy rules configuration.	A solution or program which can accomplish the following: Download the Documents from Regulators portal for 5-6 countries for Consumer & Corporate banking platform. Decipher the Rules & Configure the Rules inside the Rule Engine. Receive the Transactions & the relevant supporting documents. Optical Character Recognition (OCR) & Named Entity Recognition (NER) will be performed by the system. Perform the Rule validations in an automated way for Transactions & Documents data extracted via the OCR Engine (Currently done manually).	Project Coordinator: Gupta, Arvind shweta4.gupta@citi.com Project Mentor: Mohammad, Thanveer email TBD Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2021/22 Term 1	Citibank	Predictive Analysis of Risk Utilization - Phase II - Predictive Analysis of Risk Utilization enables Citi's clients and client facing officials to prevent regulatory violations, navigate trading disruptions by proactively take measures to prevent such breaches by allocating funds or by changing their trading strategy. Citi's institutional clients place millions of orders on any given trading day through its electronic execution platforms. As orders come in through Citi's systems, they are evaluated against several risk parameters (such as credit limits - Max Daily Notional, Daily Notional, Short Notional, etc) before the order is sent to the market. This project requires students to build capabilities to the system to predict and alert the clients of potential breach events both in isolation and combination of individual risk parameters.	Students executing this project will be expected to arrive at comparative machine learning solutions (Random Forest, LTSM and SVM) to predict imminent movement of the risk parameters based on historical trading patterns. Tasks include: Building adapters to funnel data to a central data pool to run analytics on the data. Analyzing and find inflection data points and patterns. Building a user interface/ data conduit that can be used by Citi clients/ users to be notified of any breaches if found.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Kumar, Sudeep email TBD Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2021/22 Term 1	Citibank	Equities Pre-Trade Booking Reconciliation - Equities Pre-Trade Booking is a manual task at present involving exchange dropcopy feeds, Citi’s internal trade feed for each client. The objective is to develop a tool where clients can review and confirm trades for a given product and market irrespective of execution brokers using exchange dropcopy and broker level reconciliation using blockchain which can be shared across brokers.	Equities Pre-Trade Booking Reconciliation using Blockchain Ethereum 2.0 Students to analyze the limitations and advantages of using Blockchain Ethereum 2.0 platform for financial data reconciliation. Develop UI to demonstrate the contents of 2 trade feeds at each block mutation. Give the final output at EOD in a file format with trade reconciliation exceptions.	Project Coordinator: Dossii, Shailej P shailej.p.dossii@citi.com Project Mentor: Kumar, Sudeep email TBD Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	(Not Selected) Machine Learning Model Performance - Machine learning models are being trained based on historical data. But in the commercial world, change is expected rapidly which may mark the model biased to the new data as well as scaled old data. Before the model is retained, there are immediate needs to understand what are the leverages that can be applied to interfere with the old model output to achieve the accuracy rate, then capture the business opportunity in a very short turnaround time. When models are unable to digest new data, they will generate inaccurate recommendations and predictions to the business, resulting in missing the opportunities for increased revenue.	A solution or program which can accomplish the following: Detect the root cause of low accuracy with a given model input, model output and model binary. Generate corrective recommendations to increase accuracy without re-building the model. Perform regression testing with recommendations, to demonstrate the expected accuracy. The program is expected to be able to analyse any supervisory learning model for the given input and output.	Yuqian Song, Head of APAC/EMEA Data Services and Head of Global Advanced Analytics Technology Solutions yuqian.song@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	Robo-Advisor - Student defined project. A robo-advisor that will; classify customers based on their investment experience and risk appetite, recommend a portfolio of investments to customers, provide visualizations / analysis of the customer's investment portfolio, and provide a budgeting and savings dashboard as an extension or the above.	A solution or program which can accomplish the following: Customer Classification (via chat) Portfolio Selection (recommendation to customer) Visualization (portfolio analysis) Personal Finance Dashboard (extension on top of the above)	Ravinder Rao, Senior Vice President, GCT Data & Analytics ravinder.rao@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	Private Banking Client Dashboard - Citi Private Bank (CPB) Investment Counsellors and Advisors provide frequent consultation to HNWI and UHWNI (high and ultra-high net-worth individuals) on how to manage their Investment portfolios. In order to perform their job they need high speed access to a client's positions, real-time market data and publicly available sentiment on the portfolio's constituents. The portfolio is usually composed of capital market securities and various funds (hedge, mutual, real estate, private equity). Careful thought needs to be put into providing an enriching UX / UI and leveraging machine / deep learning capability to provide robust recommendations. The users will use the information to pro-actively and also reactively service CPB's HNWI and UHNWI clients.	A working dashboard that provides a real-time view of a client's position. The view should be contextual based on the type of holdings (Cash/Liabilities, Equity, Fixed Income, Derivatives and Alternative Investments). The view would give an instrument and profitability analysis based on market data (Bloomberg / Reuters). Furthermore, there will be a recommendation engine that looks at a client's current / past positions and suggests trade-able ideas to the advisor based on upcoming announcements, trending public sentiment and client's personal interests.	Kashif Awan, Private Bank Capital Markets APAC Technology Head kashif.awan@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	Predictive Analysis of Risk Utilization - Citi's institutional clients place millions of orders on any given trading day through its electronic execution platforms. As orders come in through Citi's systems, they are evaluated against several risk parameters(such as credit limits) before the order is sent to the market. While currently, breaches in these parameters can be identified the moment the orders are placed, the next gen evolution of this risk management system requires predictive analytics of such breach events. This will enable Citi's clients and client facing officials to prevent regulatory violations, navigate trading disruptions by proactively take measures to prevent such breaches by allocating funds/ changing their trading strategy etc.	Students executing this project will be expected arrive at a machine learning solution to predict imminent movement of the risk parameters based on historical trading patterns. The solution should be able to take data feed for supplemental information (Triple witching dates, FTSE/MSCI rebalancing, other events that affect the market such as the Coronavirus threat) to more accurately predict exceptional scenarios. Tasks: Understand Citi's current data model for storing historical data. Build adapters to funnel data to a central data pool to run analytics on the data. Analyze and find inflection data points and patterns. Build supplemental data feed to establish market sentiments in the sytem and use that to augment their prediction models. Build a user interface/ data conduit that can be used by Citi clients/ users to be notified of any breaches if found.	Sudeep Kumar, Global Exchange Connectivity & Asia Cash Equities Technology Lead sudeep1.kumar@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	Customer Mailing Address Analysis - Addresses of people and businesses contain important information about them. More data about the locations of those addresses is required to get some insight from addresses. For example the population, geographic and economic indicators, crime rates etc. can be helpful. We need to collect such information about countries and cities to make the addresses usable in models and other analytics.	A solution or program which can accomplish the following: Collect information about countries from IMF data. Collect information about cities from DBPedia data. Build schedules to keep the above data fresh, as new data is available. Make this data available to lookup by country and Citi names to be used by models and analytics queries. Generate an embedding of countries and an embedding of cities, to be used as features in models. Unstructured addresses (where country, city are not marked separately, but part of large address text) need to be parsed before lookup. Make this information available by joining the addresses of people and businesses and collected data by countries and cities as join keys. Measure how much the model performance improves, after using this additional information.	Yuqian Song, Head of APAC/EMEA Data Services and Head of Global Advanced Analytics Technology Solutions yuqian.song@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg
FY2020/21 Term 1	Citibank	Marketing Audience Segmentation - Citibank sends merchants’ offers to the relevant customers. For example customers who often buy sports gear should get sports related offers and foodies should get offers from the restaurants. This requires accurate segmentation of customers as well as merchants. 3rd party data can be used to improve marketing audience segmentation.	A solution or program which can accomplish the following: Acquire 3rd party e.g. Statista, Euromonitor and map the brand mentions in the transactions, with brand master list in acquired data. Use brand category-hierarchy to segment the customers for their buying habits, using customer transaction history. Use brand category-hierarchy to segment merchants by categories of products and services sold and offers made. Use the category based segments for a broader match between customers and merchants.	Yuqian Song, Head of APAC/EMEA Data Services and Head of Global Advanced Analytics Technology Solutions yuqian.song@citi.com Project Supervisor: Dennis NG dennisng@smu.edu.sg

IS484 IS Project Experience (FinTech)

Contents

Course Description:

Course Prerequisites:

Project Timeline:

Project Team Signup Sheet:

Current Projects - FY2024/25 Term 2

Archived Projects (no longer available)

Navigation menu

Personal tools

Namespaces

Variants

Views

More

Search

Navigation

Tools