GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs

TL;DR

GraphGuard introduces a contrastive self-supervised learning framework leveraging dynamic multi-relational graphs to improve credit card fraud detection, reducing reliance on feature engineering and labeled data.

Contribution

The paper proposes a novel graph-based self-supervised approach, GraphGuard, for credit card fraud detection that operates effectively without extensive feature engineering or labeled datasets.

Findings

Effective detection on real-world and synthetic datasets.

Promising results indicating potential of self-supervised graph methods.

Reduces dependence on labeled data and feature engineering.

Abstract

Credit card fraud has significant implications at both an individual and societal level, making effective prevention essential. Current methods rely heavily on feature engineering and labeled information, both of which have significant limitations. In this work, we present GraphGuard, a novel contrastive self-supervised graph-based framework for detecting fraudulent credit card transactions. We conduct experiments on a real-world dataset and a synthetic dataset. Our results provide a promising initial direction for exploring the effectiveness of graph-based self-supervised approaches for credit card fraud detection.