Web service for detecting credit card fraud in near real-time

Abstract

This paper focuses on the design and implementation of a distributed, highly scalable, and fault-tolerant anti-fraud service accessible via REST API. Web service works in near real-time and employs machine learning algorithms for predictive analytics. Our goal is to develop an affordable anti-fraud service, which provides a possibility for participating parties (i.e. merchants, aggregating agents, payment systems, and banks) to reduce the risks of fraudulent payments over their sites. We explore a number of approaches resulting in a significant reduction of hardware and software costs as well as the size of the team working on the project.