Proposed projects

Projects proposed by Band Directors’ Association Singapore

1. Reimaging music education

Brief Description - Music educators to rethink how to deliver virtual learning experiences with activities that continue to make the music lessons engaging despite the technical nature and motivate the students in the absence of face-to-face experience due to the COVID-19 pandemic.

Objective – Achieve an effective and fun learning virtual experience for students and empower educators with tools in content creation to ease their preparation process.

Expected outcome – A digital transformation strategy that gamifies the entire learning process and allows educators to track the learning progress of students which include looking into learning needs and students’ expectations, and integrate local and overseas best practices. Students may also come up with a system to allow educators to develop their own games and learning materials vis-à-vis the students’ levels and needs. For more information, please contact ADRIAN CHIANG <president@bdas.org.sg>

Projects proposed by VMware

1. Self-service Portal for Training Platform

Project Description:

VMware’s Cloud Native Architects run activities that introduce and promote Cloud Native technologies such as Kubernetes to customers and the public. Such activities include workshops, demos, trainings, and hackathons which all leverage our Kubernetes platform. Participants are encouraged to access our platform by following lab guides and prepared instructions. However, all user access to the platform is managed by the VMware team manually prior to each session, and the task becomes increasingly tedious when there are more participants. The objective of this project is to develop a web application that will enable users to self-register and onboard to our Kubernetes platform.

Core Deliverables:

a. Standard Web Framework

i. Access Management with OIDC Integration (Google, Okta etc)

ii. User and Role Management

b.User Self-Service Kubernetes Platform Onboarding Module

i. Platform Selection

ii. One namespace for each user

iii. User Access Information to the requestor upon successful registration

c. Monitoring of System Health and User Activities

For further information, please contact be Ron at hxing@vmware.com

2. Kubernetes Cluster Management App

Project Description:

Kubernetes has become the de-facto container orchestration platform for many enterprises. Day by day, the Kubernetes ecosystem is growing, along with the number of users. Most Kubernetes Developers and Operators depend on the "kubectl" command line to manage their clusters. This is mainly accessible via desktop / laptop. However, an increasing number of people are using mobile / tablets as their secondary device for doing work, but there are not many options available on such devices. As a Kubernetes Admin/Operator, we would like to have a way to monitor and manage Kubernetes Cluster via mobile / tablet devices. As a Kubernetes Application Developer, we would like to have a way to monitor the status of the applications running on clusters and fix any issues. Hence, both VMware and the Kubernetes community at large will greatly benefit from the availability of an application for mobile / tablet devices that can help access, monitor and manage Kubernetes clusters and do quick fixes. A cross-platform app would be good solution to support both Android and iOS/iPadOS Platforms.

Core Deliverables:

The app should be able to:

- Enable access to Kubernetes clusters (kubeconfig via file, Vmware TKG/TKGi, GKE, AKE, EKS etc..).

- Show the health of Nodes

- Show the health of all Deployments

- Enable access to various Cluster Objects

- Namespaces, Pods, Deployments, Replica Sets, Stateful Sets, Services, Network Policies, Config Map, Secrets, Persistent Volumes, Persistent Volume Claims, Cluster Roles, Roles, Cluster, Role Bindings, Role Bindings

- Enable access to logs of Pods

- Optionally, provide a way to ssh into Containers

For further information, please contact be Hari at harikvemula@vmware.com

Project proposed by Shopee

1. Price Suggestion and Elasticity of Demand Analysis in Ecommerce

For ecommerce, product pricing gets harder at scale, considering just how many products are listed and sold online. One big challenge is to define the right price for different kinds of listed products. In addition, some categories or products have strong seasonal or temporal pricing trends, which need to be taken into consideration for price adjustment. For example, there is a significant price increase in masks or other personal protective products in the early stage of COVID-19 outbreak.

In this project, students are supposed to leverage some ecommerce (might be cleaned Shopee data or third-party open source data) to perform modeling and analysis related to pricing in ecommerce. The first step is to build an algorithm that automatically suggests the right product prices, based on the various features such as product text descriptions, details like product category name, previous selling records, history trend, brand name and item condition, etc. For the second step, the student needs to do some research on PED (Price Elasticity of Demand) to understand and visualize how different products’ demand changes with regard to the fluctuation of price changes.

The students need to extract data, select important features, provide insights and build data science models in this project. To demonstrate the effectiveness of the model, detailed studies and analysis will also be required.

For further information, please contact Wang Chen at chen.wang@shopee.com.

2. Causal Inference of Feature Design in E-commerce App

Background: Shopee serves as a leading e-commerce platform to facilitate small to medium enterprises to sell their products across Southeast Asia and Taiwan. To help sellers to attract buyers and make the purchase in their shop, Shopee launched a function to let sellers decorate their shops.

Problem: After white list to a few selected sellers, business need to get a scientific evaluation about how shop decoration helps sellers boost their sales. This would directly determine whether we open this function to more sellers and whether we could monetize this function. The students are expected to use a strict methodology to get the causal effect of shop decoration by building uplift models and considering real e-commerce market conditions, such as Shopee’s rapid growth, other feature changes simultaneously, sales volatility by campaign, diversity of shops and the difference from white-listed shops which are top performed.

For further information, please contact Sophia Shang at Sophia.shang@shopee.com.

Project proposed by Luye Medical Group

1. Reporting in Digital World

Project scope: Luye invites you to become a game changer to make a difference and reimage the possible! We will build a cloud-based clinician workforce productivity dashboard. Student will make use of proposed analytics skills and other digital technology to upgrade internal reporting processes and thus to get information distributed faster – at a substantially lower cost as well. The goal is to combine different technologies across the entire end-to-end reporting progress and enable reporting to become intelligent, interactive, and real-time.

Expected skills:

1. RPA 2. Chatbots 3. Visualization 4. Artificial intelligence 5. Predictive analytics 6. And more…

Learning by Doing: The project will offer students the opportunity of working in the booming industry – healthcare at post COVID time. The ex-Deloitte management consultant/paediatrician will lead and mentor the team throughout the project, conducting virtual meetings with Luye’s three markets (CN/AU/SG) leaders to define problems and craft customized solutions according to each specific culture and business natural.

For further information, please contact Dr Manaen Ma(the ex-management consultant and paediatrician) at manaen.ma@luye.com.

Project proposed by NTUC Club

1. Fun and Engaging Chatbot

Brief Description: In the leisure and entertainment industry, the chatbot will serve our members, guests and communities with a fun-love image and character. While serving the audience with personalized engagement, the chatbot is a channel for the sales and promotion of our service offerings.

Engagement - To service guests with information with regards to our entities, events, marketing and promotions via a cycle of pre, during and post engagement.

Personalization - Target guests' persona, preferences and engage them in their own customer journey. Recommend to guests the appropriate promotions, products and services.

Sales - Demonstrate cross sell and up sell capabilities via integration with the ticketing system for ticket sales.

For further information, please contact VANESSA QUEK <vanessa.quek@ntucclub.com.sg>.

Project proposed by SMU Centre for Teaching Excellence

1. Say It Right!

Personalized feedback, in the context of presentations, has the potential to help students identify key components of good presentation through highlighting high-frequency filler words, text summarization and the pace of speech, etc. Through the use of Natural Language Processing (NLP), an AI-driven application could provide analysis on a presenter's spoken words, voice, tone and provide data-driven feedback to students. These suggested prescriptive recommendations would guide students in improving their public speaking abilities through encouraging them to be self-directed in their learning.

This IS483 project aims to build upon an existing IS480 project/application, Mic-Test 1-2-3 to develop a minimal viable product and build machine learning models aimed at discovering features which contribute to a well-delivered presentation/speech. The key deliverables for the project are as follows: • Analyze presentations and rate it based on performance indicators such as Energy Levels, Emotion Tones (e.g. Anger, Disgust, Fear, Joy, and Sadness) and Language Tone (e.g. Analytical, Confident, Tentative). • Work with Subject Matter Experts (e.g. communications professors) to improve on personalized formative feedback given by the application. • Label collected audios and build machine learning models to discover features that predict the performance of a presentation.

For further information, please contact EDGE: EdTech Green-house, an initiative under SMU’s Centre for Teaching Excellence (CTE), LEONG Kwok Hing <khleong@smu.edu.sg>, Pratibha PALERI <pratibhap@smu.edu.sg>, James FOO <jamesfoo@smu.edu.sg>.

Projects proposed by L’Oréal Singapore

1. Price Optimization in E-commerce stores with Product cannibalization Analysis

Retailers have limited mediums to influence consumer behavior and running price discount has traditionally known for being the easiest to implement. Unlike advertising, price changes can be executed with little to no preparation and yet deliver immediate sales results. However this current practice led to over-discounting and further lower profit margins. It becomes unsustainable for aggressive price discounting without cannibalizing a more profitable product as consumers switch from one brand to another. Students will develop demand models for all products in L’Oréal e-commerce store and come up with an approach to pricing- incorporating their knowledge of product interactions, consumer demand, crawling of competitors’ e-commerce data, study store-wide effects on the level of discount with sales volume and period of running discounts. For further information, please contact QUARK Vivian <Vivian.QUARK@loreal.com>.

2. Data Mining for Store Build Targeting

In order to boost ROI of each store expansion within ASEAN market, L’Oréal needs to develop a deeper understanding of consumer behavior, needs, attitudes and demographics. Students will make use of data mining advances and applications to combine information from various sources such as demographics data (e.g. Age, Education level, Ethnicity, Population density), stores in neighborhood (e.g. distance apart between stores) and internal L’Oréal store data to establish characteristics of each neighborhood. This data-driven segmentations could help identify the potential reach, sales growth of each neighborhood and help to determine new location for store build. Our main focus for this project is one of the ASEAN market (e.g. Indonesia, Vietnam, Thailand, Philippines, India and Singapore) and this depends on availability of census data. For further information, please contact QUARK Vivian <Vivian.QUARK@loreal.com>.

Projects proposed by UBS AG

1. Secure coding gamification

In a world of where very public and very devastating hacks and data breaches are rapidly on the rise, increased software developer awareness of secure coding best practices is crucial to any business' success. Students will create a web game for development teams. Development teams will be able to point the game at a code repository of interest. The game will ingest that code and run best of breed open source security static code analysis tools against the repository. From there, a custom game instance will be created that presents development team with features such as: coding challenges, recorded responses, ratings, top scores, and overall analytics on the security of the repository.

For further information on any of the above projects, please contact Viramontes, Victor <victor.viramontes@ubs.com>.

Projects proposed by Credit Suisse

1. Optimal trading strategy

The student will learn the optimal trading strategy that provide the minimum expected cost of trading over a fixed period of time. The theoretical framework is minimizing a combination of volatility risk and transaction costs arising from permanent and temporary market impact. The students are expected to develop the model based on the theoretical framework and to test the model performance by using intraday trading data in the stock market. We will guide students on both modeling and testing to complete this project.

2. Catastrophe stress testing

The student will learn to assess the financial risk of a bank under catastrophe events such as earthquake, tsunami, pandemics and flood. The assessment methodology is based on catastrophe risk model framework developed by the insurance industry. The students will develop the model as well as test the model performance by using historical data such as actual losses, direct and indirect impacts on the economy, corporations, and financial industry due to the catastrophes. We will guide students on both modeling and testing to complete this project.

3. Inflection point indicator - Currency crisis

The student will learn to predict the currency crisis of a country. The currency crisis predictive model is developed based on machine learning algorithm on historical financial and macroeconomic data. Currency crisis is defined as currency depreciation of at least 25% over a one month period. Relevant data for various countries are FX rate, external debt - short term, External debt – total, Current account deficit, inflation, foreign-direct investment, portfolio or other investment inflows, foreign currency reserves, level of M2/reserves, real interest rate, GDP, equity Index, export and import. We will guide the students both on the modeling and testing to ensure the success of this project.

For further information on any of the above projects, please contact Chew, Eric <lengsiang.chew@credit-suisse.com>.