Large Scale Modelling and Analytics Challenges at a Payments Company
Submitted by subhajit sanyal (@subhajit) on Friday, 4 July 2014
Section: Full talk Technical level: Intermediate
This talk first presents a broad overview of the Big Data challenges in a payments company. Then it discusses in details an application around modelling spend behavior of credit card holders. Through the application the talk demonstrates how various machine learning and data mining techniques are utilized to glean insights from petabyte scale data, and how one build practical models to solve real world problems.
At American Express, we serve tens of millions of credit card members who transact at several million merchants globally. Apart from this transaction level data, there is petabyte scale data generated from card members' other interactions with American Express:- through visiting and interacting with our website, phone and chat interactions with customer care representatives, the surveys we conduct to gauge the pulse of our customers, etc. All these result in large scale data coming from multiple modalities. In this talk, we will focus on some key challenges which arise from dealing with this data. The talk will first give a broad overview of the various challenges in the context of machine learning in the payments industry and then focus in some details on a particular problem of modelling purchase intent of credit card holders.
Though this talk is pitched at a broad overview level, it may be helpful to have some basic familiarity with popular machine learning and data mining techniques.