An improved BiGAN model for anomaly detection in finance

Abstract

Financial systems play a pivotal role in shaping contemporary society, and the detection of financial anomalies holds immense significance in mitigating the adverse repercussions of market uncertainties on the global economy. In this context, this study presents an innovative LSTM-GANs model, specifically crafted to enhance the detection of anomalies in financial stock markets. The model introduces an "Anomaly Score" as a pivotal metric, which is computed through a combination of factors such as Reconstruction Loss, Latent Space Distance, and Discriminator Score. This composite score provides a quantitative assessment of the anomaly level within the financial data. By applying a predefined threshold to this Anomaly Score, the model efficiently identifies and flags anomalies. In a world where financial markets are increasingly complex and prone to unexpected events, the ability to detect and respond to anomalies swiftly is paramount. This novel LSTM-GANs model offers a promising approach to bolster the accuracy and effectiveness of financial anomaly detection, thereby contributing to the stability and resilience of global financial systems.