Connecting The Dots To Combat Collective Fraud

TL;DR

This paper presents a real-time risk control system leveraging graph databases and query languages to detect and combat coordinated collective fraud in online platforms.

Contribution

It demonstrates how to build an effective, real-time collective fraud detection system using TigerGraph and GSQL, integrating data science and fraud expertise.

Findings

Successful implementation of a graph-based fraud detection system

Real-time detection capabilities demonstrated

Enhanced coordination between data scientists and fraud experts

Abstract

Modern fraudsters write malicious programs to coordinate a group of accounts to commit collective fraud for illegal profits in online platforms. These programs have access to a set of finite resources - a set of IPs, devices, and accounts etc. and sometime manipulate fake accounts to collaboratively attack the target system. Inspired by these observations, we share our experience in building two real-time risk control systems to detect collective fraud. We show that with TigerGraph, a powerful graph database, and its innovative query language - GSQL, data scientists and fraud experts can conveniently implement and deploy an end-to-end risk control system as a graph database application.