A Spatial-temporal Gated Network for Credit Card Fraud Detection

Timely and accurate credit card fraud detection (CCFD) is concerned by all financial institutions. Existing CCFD methods generally employ aggregated or raw features as their representations to train their detection models. Yet such features tend to fall short of effectively exposing some critical characteristics of frauds. In this work, we propose a spatial-temporal gated network (STGN) to automatically learn new informative transactional representations containing users' transactional behavioral information for CCFD. A special gated recurrent neural net unit is constructed with a time-aware gate and location-aware gate to extract users' spatial and temporal transactional behaviors. A spatial-temporal attention module is designed to expose the transaction motive of users in their historical transactional behaviors, which allows the proposed model to better extract the fraudulent characteristics from successive transactions with time and location information. A representation interaction module is offered to make rational decisions and learn compositive transactional representations. A real-world transaction dataset is used in our experiments to verify the efficacy of the learned new representations. The results demonstrate that our proposed model outperforms the state-of-the-art ones, thus greatly advancing the field of CCFD.