Speaker "Nitesh Kumar" Details Back



Decisioning system in FinTech


Fintech companies have to process multiple decisions in real time or near real time. These online decisions directly impact the magnitude and flow of money. In my talk, I will describe how decisioning works in such an environment. At a high level, I will explain the decisioning system evaluates the likelihood of fraud and credit default and how it can be viewed as an amalgamation of rule based decisioning, machine learning and more specifically active learning. Unlike most other applications, this decisioning system does not get instant feedback on the decisions it makes. Moreover, the decisioning impacts what future iterations of the system can learn upon. In this talk, I will explain how to get around these problems and emphasize how we can do so in an interpretable, transparent fashion.


Nitesh is the Director of Data Science at Affirm where he is responsible for the online decisioning system that provides loans to help consumers make online purchases. Before Affirm, Nitesh was building machine learning algorithms to help democratize data science at Skytree. He holds a PhD in mathematical finance and has been practicing analytics and data science for over 9 years. In his free time, he dabbles in the stock market and bets on rare events.