# Boundary-aware dual-discriminator generative adversarial network for data augmentation in financial transaction fraud detection

## TL;DR

This paper introduces BADGAN, a new GAN-based method for improving fraud detection by generating realistic synthetic fraud data.

## Contribution

BADGAN introduces a boundary-aware dual-discriminator mechanism to enhance synthetic fraud sample quality near decision boundaries.

## Key findings

- BADGAN outperforms existing methods in handling class imbalance in financial fraud detection.
- Synthetic samples generated by BADGAN improve the downstream classifier's ability to detect fraud.
- Experiments on real-world and public datasets validate BADGAN's effectiveness.

## Abstract

The rapid growth of digital payments exacerbates the challenges in Financial Transaction Fraud Detection (FTFD). These challenges stem primarily from an extreme class imbalance, where legitimate transactions greatly outnumber fraudulent ones. This imbalance significantly hampers the ability of FTFD models to accurately learn fraud patterns. Although existing data augmentation techniques have shown effectiveness in alleviating this problem, they are often negatively influenced by anomalous samples that diverge from the true fraud distribution due to fraudsters’ concealment strategies and the inherent complexity of fraudulent patterns. This divergence makes it challenging to accurately model the distribution of fraudulent activities. In this work, we propose a Boundary-Aware Dual-discriminator Generative Adversarial Network (BADGAN) to address the class imbalance issue in FTFD. BADGAN integrates a boundary sample classifier with a dual-constraint mechanism based on distance adversarial learning, allowing the generator to produce synthetic samples that both adhere to the distribution of real fraud data and maintain a distance from the decision boundary. This boundary-aware design emphasizes the optimization of sample quality near classification boundaries, thereby improving the downstream classifier’s ability to distinguish fraudulent behavior. Extensive experiments on both real-world and public datasets demonstrate that BADGAN outperforms its competitive peers in addressing the class imbalance issue, thereby enhancing the detection performance of FTFD models.