Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks

TL;DR

This paper explores using Generative Adversarial Networks to generate synthetic credit card fraud data, enhancing classifier performance and stability, with Wasserstein-GAN showing superior results.

Contribution

It introduces GAN-based oversampling for fraud detection and compares different GAN variants, highlighting Wasserstein-GAN's stability and realism.

Findings

Wasserstein-GAN produces more realistic fraudulent transactions.

GAN-based oversampling improves classifier discrimination.

Conditional GANs with k-means clustering do not outperform non-conditional GANs.

Abstract

In this study, we employ Generative Adversarial Networks as an oversampling method to generate artificial data to assist with the classification of credit card fraudulent transactions. GANs is a generative model based on the idea of game theory, in which a generator G and a discriminator D are trying to outsmart each other. The objective of the generator is to confuse the discriminator. The objective of the discriminator is to distinguish the instances coming from the generator and the instances coming from the original dataset. By training GANs on a set of credit card fraudulent transactions, we are able to improve the discriminatory power of classifiers. The experiment results show that the Wasserstein-GAN is more stable in training and produce more realistic fraudulent transactions than the other GANs. On the other hand, the conditional version of GANs in which labels are set by k-means clustering does not necessarily improve the non-conditional versions of GANs.