A GAN-based Hybrid Sampling Method for Transaction Fraud Detection

Transaction Fraud Detection (TFD) is a vital aspect of contemporary financial security, significantly challenged by class imbalance, as legitimate transactions vastly outnumber fraudulent ones. This imbalance challenges TFD models in effectively learning fraudulent patterns. Traditional over-sampling techniques, while effective in addressing class imbalances, encounter difficulties in TFD due to the concealment of fraudsters, resulting in increased behavioral overlap between fraudulent and legitimate transaction patterns. In this work, we introduce a novel generative adversarial network-based hybrid sampling method (GANHS) that first employs over-sampling through a dual-discriminator generative adversarial network (D<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> GAN) to generate a balanced transaction dataset. Subsequently, an adaptive neighborhood-based under-sampling method is employed to refine the generated samples, eliminating those that exacerbate behavioral overlap. Our method not only generates samples that closely resemble the actual distribution of fraudulent patterns but also markedly reduces the impact of behavioral overlap, thereby enhancing the detection of highly concealed fraudulent transactions. Experimental results on a large-scale real transaction dataset demonstrate that our proposed method outperforms its competitive peers, highlighting its potential to advance the effectiveness of TFD systems.