YES Bank looks to strengthens ML, data analytics ecosystem with Datathon
The Datathon initiative looks to harness innovative machine learning and data analytics solutions and integrate it with the technology framework of YES Bank to enhance its customer service.
Leading private lender YES Bank, in its drive towards strengthening the technology ecosystem in the area of data analytics and machine learning in the country, held its flagship YES Datathon event in Bengaluru recently.
The YES Bank Datathon started out as an industry-first initiative in September this year to crowdsource data driven solutions from leading data scientists and analysts. The finale of the Datathon was held on December 22-23.
The initiative saw participation from over 6,000 data scientists, engineers and developers who participated in various Machine Learning challenges. The 200 top data scientists identified from the challenges were given 60 days to create a working data model or a prototype which would be trained, tested and deployed by the bank by January.
The Datathon had a total of 200 teams participating. Students from top technology institutes such as IIT Bombay, Chennai, and Kharagpur and ISI Kolkata, along with professionals from organisations like IBM, Walmart Labs, Siemens and Amazon Development Centre, among others participated in the Datathon.
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. The YES Bank Datathon provides us with an opportunity to engage with 6000+ data scientists. It has helped identify newer use cases as well as statistical techniques and incorporate cross-industry best practices.”
At the finale, 50 teams showcased their models which were trained and tested on more than a terabyte of created and tokenized datasets and 10 solutions were awarded cash prizes worth Rs 20 lakh.
The key use cases on which applications were developed include predictive service delivery for customers, a sales recommendation model for relationship managers, customer transaction relationship graph, and fraud detection and analytics for card customers.
Twenty models will be identified at the finale by the bank and it will work with the teams to take it live within a month. The remaining models will move to the bank’s data product library and will be iteratively developed and taken live within a three-month period.
YES Bank’s Datathon is also looking to partner with technology institutes such as IITs and BITS Bombay, and will also host AI/ML challenges and data engineering workshops to deepen practical and technical knowhow of future technology leaders and widen the data science ecosystem.