Exploring Anomaly Detection and Risk Assessment in Financial Markets Using Deep Neural Networks

Abstract

In this paper, deep learning technology, along with a Gated Recurrent Unit (GRU) combined with an attention mechanism, is used to enhance the recognition ability and risk assessment accuracy of abnormal trading behavior in financial markets. The GRU effectively solves the problem of gradient vanishing in traditional recurrent neural networks through its unique gated structure, allowing the model to learn more stable and effective feature representations in long sequence data. On this basis, the contextual attention (CA) module in the attention mechanism is introduced, enabling the model to automatically learn and assign different weights to various parts of the input sequence. Combined with bidirectional GRU and the attention mechanism, the model can not only capture temporal dependencies in the sequence, but also highlight the key features that affect market anomalies, thus improving the model's ability to understand complex market dynamics.