arrow_back How we build highly scalable and multi-tenant orchestration service using Apache Airflow on Kubernetes
Automating Workflows for AI Projects arrow_forward
Defining and Solving Data Science for Finance Problems: A Case Study
Submitted by Aniruddha M Godbole (@godboleam) on Tuesday, 7 May 2019
Session type: Full talk of 40 mins
In this talk the speaker shares his understanding about the challenges of applying Data Science for Finance, takes an example in which he was involved in formulating a challenging problem and where cutting-edge Machine Learning research was used. Finally, the speaker offers his thoughts on how to go about formulating Data Science for Finance problems.
This talk will be tentatively be organized around four sections.
1. Why is it hard to formulate Data Science problems for Finance.
2. A specific problem: Why is service quality ignored in Finance and its relevance.
3. Technical Challenges: Why this specific problem is tough and how State of the Art Machine Learning and Traditional Statistics may be used.
4. How to formulate Data Science for Finance problems: Some sketchy thoughts…(this is partly art, partly science)
Aniruddha M Godbole has expertise in Finance, Computer Science and Statistics. Over the last 14 years he has worked in a bank, a financial risk managment consulting firm, and in the IT industry. Aniruddha has an MBA in Finance from National Institute of Bank Management and a MS in Data Science from Indiana University. Recently Aniruddha and his research supervisor Professor David Crandall authored a paper titled ‘Empowering Borrowers in their Choice of Lenders: Decoding Service Quality from Customer Complaints,’ ACM International Web Science Conference (WebSci), 2019. He has been consulted by the Central Bank on a financial innovation. He has contributed to the Opinion Pages of a major business newspaper on numerous occasions. Aniruddha is also the inventor of a mobile payments solution for basic mobile phones (patent application filed).