Oracle

The team has worked on a ‘master product’ which creates a single 360 degree view of every retail customer , and also provides customized product and service recommendations for every individual customers – (including product propensity/predictive service delivery/service resolution etc
To create the ML recommendation engine they have used individual and cluster wise product propensity and a cluster correlation technique. The solution will allow the bank to provide customized and predictive products and services to each and every customer, as well as allow sales managers to cluster their clients based on the propensity model

Insights

The team sas developed a unique model basis , using a modified version of Shapley’s value – called Shap Value to create a customer – product/service propensity model basis product holdings/demographics/transactions. For eg. the propensity of a customer with 2 FD holdings towards an MF investment. This model combined with Team Oracle creates a comprehensive Next Best Action model

Finance Data Dons

Product 1 : The team has created a data model which creates a personal finance management tool for every customer using transaction patterns as a base. The application will have the ability to predict and classify transactions as well as smart investment advisory once implemented

Product 2: The model will help optimizing Merchant relationships – both online and offline retailers. The team has used ML to cluster POS transactions and identify anomalies in transaction volume and volume. This will help to increase POS/gateways, identify new merchants, provide merchant offers

Django Unchained

The team has created an AI based application for relationship managers (sales representatives) of the bank which will enable them to measure share of wallet for the bank for every retail customer, predict attriction as well as provide customized products/services

Billa

This team has created a master algorithm which can form the basis/foundation of other data models. Basically, this model which takes a cue from representation learning helps to tag, classify and then sort data in a much quicker and innovative way. Almost 70% of the time spent by any data scientist on creating a working prototype goes in cleaning, tagging and classifying data. This model will help accelerate that process and remove manual involvement in the same.

Reverse Atlas

The team has worked on a unique ML algorithm (which finds usage on streaming sites) which helps identify customer relationships basis transactions and creating relationship trees for every customer basis transactions. This would help identify and target new customers with exact products/solutions/offers as well as deepen current relationships

This almost creates a social media like network using Financial transactions and demographics as the base. This is the first time this algorithm which finds usage in streaming sites will find an application in the financial services space.

NLP Rockers (TCS)

Uses NLP and clustering methods to convert email service requests into service tags across the entire customer bases and subsequent clustering and prioritization. The model then uses predictive analytics to create customer clusters and predict service requests per cluster

Zessta

This product works on lowering customer attrition using a clustering algorithm which identifies customers most prone to attrition.This product works on lowering customer attrition using a clustering algorithm which identifies customers most prone to attriction also measures the affinity/non-affinity of customers to products to help predict next best action for customers for both dormant and active customers

Avensis

Chat bots have been quicker and better but a missing link has been customization. This solution will help YES BOT provide more customized responses to customers/non customers using demographic and account data, while also providing regular services like payment reminders/EMI tracker and relevant investment notification

Meson Labs

This product takes a unique approach to managing finance and investment using neural networks to create human like learning as well as use Google adwords to help classify transactions since transaction markers are often commonly known brands or words. This helps create a relevant map of all transactions for individual customers, comparison of spends and investments and accordingly provide advisory”

Prayaas

The team has worked on 2 solutions, the first one helps manage and predict individual customer deliveries like cards/statements/tax statements/cheque books – providing proactive service, reducing human involvement and as a result reducing service requests

Data pirates

The model provides an alternative method to score and profile customers , pooling in LinkedIn APIs and other external APIs to help score customers who are currently not scoped by CIBIL

GSA07

A major problem that bank customers face is to connect to the bank to avail a service, address any queries or resolve an issue. To address this concern this model will put in place which anticipates a customer’s concern based on his demographics and transaction data and allows the bank to reach to their customers with a solution before the customer knocks at their door with a problem.

Fakedata

The model uses machine learning to create a customer satisfaction or ‘happiness index’ , and basis affinity of customers to products or brands (basis transactions) – provides customized offers/offering as well as enables more nuanced and targeted marketing

Data Ninjas

Team has worked on use cases for properly classifying merchants based on there business category(Wallet, E.Commerce, Online Shopping, etc.) and then using the result to get to know the affinity of a customer segment with a particular merchant.

For Merchant classification, they used 2 approaches, unsupervised clustering approach to cluster merchants on correct spelled centroids and second approach to hit Google search API and doing POS tagging to cluster based on Nouns and adjectives. For checking user affinity they used RFM model.

1. Data Wizards – Team Oracle

2. Data Acers :

a. Team Billa
b. Team Insight
c. Team Finance Data Dons
d. Reverse Atlas & Django Unchained

3. Data Pros

a. Team Seg Fault
b. Team WLP Rockers
c. Team Data Ninja & Zessta
d. Team Data Pirates & GSA 07

4. Data Champs – Team Insight

Step 1: Click here ‘Join the Datathon’ – you will be led to our datathon partner – Skillenza’s page for the YES BANK Datathon

Step 2: Click ‘Register’ and enter details required to sign up

Step 3: Get your crew together and form a team – we recommend cross-disciplinary teams (max. 4 members) comprising Data Scientist, Big Data Engineer, Coder, Full Stack Developer to register

Step 4: Once completed, you will get a confirmation mail from Skillenza. Happy data diving!

Rajat Kanwar Gupta

President
Business & Digital Technology
YES BANK

Mathangi Sri

Head Data Science, Phonepe

Vaibhav Gupta

Director, EY

Hindol Basu

CEO, Actify Data Labs

Biswa Gourav Singh

Lead ML Engineer, Capillary Technologies

Ajay Ohri

Specialist Platform
SAPIENT AI PRACTICE

Subrat Panda

Principal Architect, AI Technologies
Capillary Technologies

VARTUL MITTAL

Technology & Innovation Specialist

Gaurav Daftary

Quantitative Analyst
Moody’s Investor Services

Farhat Habib

Director, Data Sciences
Inmobi

Subramanian M S

Head of Analytics
bigbasket.com

Yogesh Joshi

CIO

Kores India

Nitin Sareen

Head of Analytics Solutions & Delivery

Aditya Birla Group

Nimilita Chatterjee

Sr. Vice President-Data & Analytics

Equifax

Ratnakar Pandey

India Head Analytics & Data Science

Arpit Agarwal

Associate Director, Data Science Zoomcar

Sayan Sen

Head – Data Labs

HDFC Life

Subhabrata Sinha

Assistant Vice President, Insurance Analytics Genpact

Saurav Gandhi

Director – Credit Risk and Data analytics – PayU

Rohit Pandharkar

Head, Data Science & AI, Mahindra Group

Tanuj Taneja

Associate Director

Kvantum Inc.

Ananda Rao Ladi

Chief Learning Officer

Edureka

Mukesh Jain

Vice President & Head – Data Technologies

Capgemini

Saurav Kaushik

Data Scientist

Uber