Yes Bank Datathon Brings 20 Data-Driven Products at India’s First Brand-Led Datathon

India's first Bank-led Datathon powered by Yes Bank aims to augment the bank's embedded data analytics & ML units to drive rapid prototyping of AI/ML-based products, optimize digital product suite, and enhance product/service design and delivery, in an accelerated 100-day period.

Bengaluru | 26.12.2018: Yes Bank organised India's first Bank Led Datathon – The Yes Bank Datathon on December 22-23 in Bangalore, with a focus to reach out to the global developer, coder and the data science community to work on the bank's data stacks using curated, tokenized and anonymized data

This is India's first Bank-Led data science hackathon and saw a participation of over 6000+ data scientist/engineers and developers in its inaugural session. The initiative identified 200 top data scientists from the challenges who were given 60 days to create working data models/prototypes which will be trained, tested and eventually go live within a month.

The Datathon saw the maximum participation from the professional community apart from the crème-de-la-crème of student participation from the top tier institutions. The top 200 teams included students from top technology institutes like IIT Bombay, Chennai, Kharagpur, and ISI Kolkata. 150+ professionals were representing organizations like IBM, Amazon Development Centre, Capillary Technology, TCS, Accenture, Amdocs, Walmart Labs, Siemens, and Infosys among others, who worked on the data science hackathon challenge beyond their professional commitments.

The professionals saw this event as an opportunity to work on a variety of use cases involving voluminous data and viewed this opportunity as a major driving force for their further learning. The participating students looked forward to the Yes Bank Datathon to build algorithms and data models on Terabytes of real data in a deployment-ready environment. The cloud environment for the Datathon was provided by YES BANK, through its partners Amazon Web Services and Cloudera, which mirrored its own data engineering environment.

The participants developed model applications on key use cases including Predictive service delivery, Sales recommendation model for Relationship manager, Customer Sentiment Analysis to predict Customer Engagement, Next Best Action model, Customer Transaction Relationship Graph, Fraud detection and analytics for card customer, Transaction Pattern Development for Merchant and customer anomaly detection and Performance Finance Management Tool using Recurring Payment Predictions.

The Event saw the involvement of 25+ external mentor pool created by the bank to help teams into every step of the way. Data science heads and experts from diverse backgrounds and industries across core analytics, e-commerce, manufacturing and consulting came together to assist participants in every step of the process.

External Mentors included industry biggies like Gaurav Aggarwal (Ola), Saurav Kaushik (Uber), Mujtaba Hasin, (Yatra.com), Mathangi Sri (Phonepe), Subramaniam MS (Big Basket), Farhat Habib (Inmobi) Karthikeyan NG (Chumbak), Arun Kumar (Groupon), Arpit Agarwal (Zoomcar), Nithin Sareen (Aditya Birla Group), Rohan Pandharkar (Mahindra & Mahindra), Gaurav Daftary (Moody's Investor Services), Nimilita Chatterjee (Equifax), Mukesh Jain (Capgemini), Ajay Ohri, Sapient (author of Python for R Users/ Poets n Hackers), Hindol Basu-  Actify Labs (Former Head Data Analytics Citi Bank) , Subrat Panda (Capillary Technology) and Ananda Lali (Edureka)

At the finale, the 200 data science professionals from top 50 teams showcased their final products which were trained and tested on more than a terabyte of created and tokenized datasets. The best solutions won cash prizes worth INR20 lakh and the top 20 models identified by the bank will be taken live within a month and the remaining models will move into the bank's data product library and iteratively developed and taken live within a three-month period

The winning team from Oracle was adjudged as 'Data Wizards', for creating a 360-degree model for profiling of every customer to predict next best action. Team Insight from Sri Lanka was adjudged as the best student team bagging its place as one of the top 5 teams. This team developed a model for predicting customer product and service affinity. The other teams in top 5 were Finance Data Dons, Reverse Atlas and Django Unchained, who developed models on Predictive Payments to create a Personal Finance and Investment Management Tool + POS Anomaly Detection, creating a community akin to social media sites using transaction analysis and Predictive model for customer relationship managers to target existing and new customers using transaction nodes, respectively.

Commenting on the event, Rajat Monga, Senior Group President, Financial Markets, YES BANK, said "YES BANK embarked on a data centered business model as part of our TechTonic initiative and now has a full stack of technology and talent capability built up. In order to leap frog on this data native transformation, YES Datathon provides us with an opportunity to engage with 6000+ data scientists. It has helped us identify newer use cases as well as statistical techniques and also incorporate cross-industry best practices".

Going forward, YES BANK will host AL/ML challenges and has partnered with top IITs and BITS Bombay. In addition, the bank plans to host data engineering workshops to deepen practical and technical know-how of future technology leaders and widen the data science ecosystem. The bank will host 6 Machine Learning challenges in partnership with IITs/BITS that will lead up to the YES Datathon 2019 to be hosted in June 2019

Datathon is a platform for YES BANK to hire and train budding talent in the data science domain to ultimately create a 100 + team of data scientists, developers and coders as part of their YES TechTonic Initiative. This 100 people strong team Techtonic will identify, evaluate and build strategy, evaluate future tech, plan and manage projects and bring about a data-driven approach to build innovative products in-house to create an ecosystem of leaders and learners, called YES DATA Community. This nationwide community of industry leaders, students and professionals is a first of its kind initiative to boost the conversation of data science in India.YES DATA community will serve as a platform for constant knowledge sharing and crowdsourcing of new ideas and concepts on future technologies.