IS484 IS Project Experience (FinTech)

Course Description:

IS484 is cancelled for AY2021/22 Term 2. Will resume in AY2022/23 Term 1.
Please seek sponsors and plan for IS483 for AY2021/22 Term 2.

• 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.

Project Timeline:

Activities	Timeline	Term 1/ Term 2	Action By
Project Sourcing and Registration	Week -16 to Week -8	Form teams. Review the below set of predefined projects provided by CitiVentures. 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
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	Presentation. 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 7 to 9	Presentation	Students, Supervisor, Reviewer (Optional: Sponsor, Track Coordinator)
Finals	Week 13 to Week 16	Presentation	Students, Supervisor, Reviewer (Optional: Sponsor, Track Coordinator)

IS484 Project Wiki:

Project teams to maintain their documentation here:
IS484 Project Wiki Home Page

Project Team Signup Sheet:

AY2020/21 Term 1
https://docs.google.com/spreadsheets/d/1IDAhC4JiK3RuKnIDQMG5UjJ6I1IiImo81Lu13wAuUxE/edit?usp=sharing
AY2020/21 Term 2 - CANCELED
https://docs.google.com/spreadsheets/d/1IDAhC4JiK3RuKnIDQMG5UjJ6I1IiImo81Lu13wAuUxE/edit#gid=1043528005 - CANCELED
AY2021/22 Term 1
https://docs.google.com/spreadsheets/d/1IDAhC4JiK3RuKnIDQMG5UjJ6I1IiImo81Lu13wAuUxE/edit#gid=86226209
AY2021/21 Term 2 - CANCELED
IS484 will resume in AY2022/23 Term 1

Citibank Projects

Item	Project Sponsor	Project Description	Project Deliverables	Project Sponsor/Stakeholders
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 Sponsor: Awan, Kashif
2	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 Sponsor: Balusa, Ashok
3	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 Sponsor: Mohammad, Thanveer
4	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 Sponsor: Kumar, Sudeep
5	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 Sponsor: Kumar, Sudeep

Archived Projects (no longer available)

Item	Project Description	Project Deliverables	Project Sponsor/Stakeholders
X	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
X	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
X	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
X	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
X	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
X	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