Graph Networks - 10X investigation with Graph Visualisations

Summary

Fraud detection traditionally required investigators to manually combine large datasets from disparate anti-fraud systems using statistical methods, which proved slow and inefficient. Grab built an interactive Graph Visualisation platform to transform raw records into connected visual maps without requiring manual queries or switching tools. The platform manages over three billion nodes and edges, allowing investigators to selectively expand data points and replay chronological events using temporal filters. Visual relationship mapping helps teams verify account appeals, uncover device-sharing rings, and spot anti-money laundering behavior through transaction density patterns.

Takeaways

1. 1

   Grab's graph storage system maintains more than three billion nodes and edges, using on-demand node expansion to display data selectively rather than rendering the entire dataset at once.

2. 2

   The platform includes an interactive time filter for timeline tracking and history replay, allowing investigators to observe temporal relationships and event chronology from a chosen starting point.

3. 3

   Visualizing relationship density enables fraud investigators to differentiate between false positive account alerts and real fraud networks, such as heavily shared physical devices or suspicious transfer patterns to payment providers.