Credit Card Fraud Detection Based on Unsupervised Attentional Anomaly Detection Network

In recent years, with the rapid development of Internet technology, number credit card users has increased significantly. Subsequently, fraud caused a large amount economic losses to individual and related financial enterprises. At present, traditional machine learning methods (such as SVM, random forest, Markov model, etc.) have been widely studied in detection, but these are often difficulty demonstrating their effectiveness when faced unknown attack patterns. this paper, new Unsupervised Attentional Anomaly Detection Network-based Credit Card Fraud framework (UAAD-FDNet) is proposed. Among them, fraudulent transactions regarded abnormal samples, autoencoders Feature Attention GANs used effectively separate them from massive transaction data. Extensive experimental results on Kaggle Dataset IEEE-CIS demonstrate that proposed method outperforms existing detection methods.