Risk gated graph neural network improves credit card fraud detection
RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection
Machine Learning
Summary
Credit card fraud is hard to catch because fraudsters try to hide their actions among many normal transactions. The authors show that fraudulent transactions often share links like accounts or devices, which can be used to find them. They created a new method that uses a special kind of network to focus more on risky transactions when analyzing how transactions connect to each other. This approach helps detect fraud better than standard methods when tested on a well-known dataset.
What this means in practice
- •For financial fraud analysts: Improve fraud detection systems by integrating risk-weighted graph analysis of transaction links to identify hidden patterns.
- •For cybersecurity operations teams: Enhance monitoring tools by using risk-gated message passing on transaction graphs to detect suspicious network behavior.
Tested on one dataset.
Authors
Mythreyee Hari, Subin Sahayam, Vegesna S M Srinivasavarma
Abstract
Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are continuously evolving, with fraudulent transactions often disguised to resemble legitimate activity. Real world transaction data for fraud detection is severely affected by class imbalance making it harder to detect these transactions. Fraudulent transactions are rarely isolated. Accounts, devices, and other common attributes are often shared across fraudulent activity, revealing relational patterns that individual transaction features alone cannot capture. Graph-based approaches model these relationships explicitly. However, standard graph neural networks aggregate neighbourhood information uniformly, which can dilute the already scarce signal carried by fraudulent transactions and limit detection of camouflaged fraud. This work presents RGH-GNN, a heterogeneous graph neural network that addresses this limitation by incorporating transaction-level risk scores, generated by a supervised LightGBM classifier as edge weights. It is used to guide message passing through a learnable risk-gated aggregation mechanism. It ensures that high-risk transactions contribute more strongly to learned representations rather than being diluted by uniform neighbourhood aggregation. RGH-GNN is evaluated on the IEEE-CIS fraud detection dataset against standard graph neural network models that are trained on the same heterogeneous graph. RGH-GNN outperforms all baselines across every evaluation metric, with an AUC-ROC score of 0.914. This demonstrates that incorporating engineered risk signals into graph-based message passing substantially improves fraud detection performance.