iCubed (Institute, Industry, Innovation) seminars invite DSI Industry Affiliates to give technical talks on work going on in their domain. Join to learn about real-world uses of data science and opportunities with Industry Affiliates.
Guest Speaker
Samuel Sharpe, Machine Learning Research Scientist, C4ML Applied Research at Capital One
Moderated By: Jessica Rodriguez, Industry Engagement and Outreach Officer, The Data Science Institute
Dynamic Customer Representation Learning in Finance
Digitization has made its way into the financial services industry with the explosion of online services for credit cards, rewards, loans, banking, investing, and budgeting. Innovation in this field has roughly mirrored similar trends in ecommerce, where ecommerce companies have mastered personalization, marketing, and efficiency. From providing automated customer service to alerting customers about potentially fraudulent transactions, all the necessary services we provide are only improved by having a deep understanding of our customers. Online activities on web and mobile apps open a completely new lens through which to gain this understanding. Not only is digital activity always changing, but similar to transactions, these activities are highly dimensional and require feature engineering for specific tasks. In our recent paper accepted to the ICML 2021 Workshop on Representation Learning for Finance and E-Commerce Applications, Dynamic Customer Embeddings for Financial Service Applications, we explored methods to learn dynamic representations of user online activity to simplify and improve utilization of digital activity data in downstream applications. We test our framework on real Capital One data, improving three prediction problems: a customer’s next digital session intent, customer likelihood of calling a call center, and fraudulent digital session detection.
Bio: Sam Sharpe is a Machine Learning Research Scientist in the Applied Research group at Capital One where he contributes to research and application in the areas of GraphML, Explainable AI, and Sequence Modeling. Before joining Capital One he worked as a Data Scientist at MLB and Booz Allen Hamilton. He is a proud Columbia University alum, receiving both his M.S. in Computer Science and B.S. in Operations Research from CU.
