# Graph Networks - Striking fraud syndicates in the dark

[Grab](https://yomu.fyi/company/grab) · Muqi Li · Apr 28, 2022

**Type:** Problem & solution

## Summary

Grab's Integrity team faced escalating threats from organized fraud syndicates operating device farms and GPS spoofing tools that mimic normal user behavior. To overcome the limitations of traditional rule-based systems, Grab built a Graph-based Prediction Platform that links entities across shared attributes to expose hidden network structures. The architecture includes a scalable graph database platform holding over one billion nodes, powering real-time graph visualization for analysts alongside a configurable network feature extraction system. In addition, the team deployed Graph Neural Networks to capture structural correlations across transaction networks. These systems collectively help detect coordinated promo abuse, payment fraud, and complex money laundering schemes.

## Context

Professional fraud syndicates using device farms and GPS spoofing apps camouflage as legitimate users, making them difficult to detect through traditional rule-based scoring systems.

## Approach / What changed

Implementing a Graph-based Prediction Platform featuring a graph database with over one billion nodes, real-time visualization tools, a network-based feature engine, and Graph Neural Networks for anti-money laundering and fraud detection.

## Takeaways

- Graph systems distinguish benign sharing patterns from large-scale syndicate operations by analyzing wider network connectivity rather than isolated entity pairs.
- Grab's Graph Database Platform stores over one billion nodes to power real-time visualizations across more than 10 feature dimensions and compute network metrics such as hop counts.
- Graph Neural Networks leverage structural correlations across transaction graphs to identify multi-stage money laundering and coordinated syndicate activity.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [AWS](https://yomu.fyi/topic/aws), [Machine Learning](https://yomu.fyi/topic/machine-learning), [Scalability](https://yomu.fyi/topic/scalability)

[Read original post](https://engineering.grab.com/graph-networks)