Intelligent Anti-Money Laundering Transaction Pattern Recognition System Based on Graph Neural Networks

Abstract

This paper presents a new Intelligent Anti-Money Laundering Transaction Pattern Recognition System based on Graph Neural Networks (GNNs). The proposed system addresses the limitations of traditional anti-money laundering (AML) by leveraging the power of image representation and deep learning techniques. We introduce general methods for creating financial networks based on different shapes, including structural and physical. A custom GNN architecture is designed, featuring heterogeneous graph convolution, listening mechanisms, and physical models to capture the exchange patterns. The system uses advanced engineering techniques to extract both local and global features of financial performance. The analysis of the world's big data shows that the best performance of our method, achieved 35.2% Money Laundering Detection Rate (MLDR) in the top 1% of business flag, do better way. The model interpretation is improved by analyzing the SHAP value, providing insight into the decision-making process. Case studies show the system's ability to uncover financial transactions, including deposits from cryptocurrency exchanges and smurfing operations. This research contributes to the advancement of AML practices by introducing more accurate, flexible, and effective solutions for investigating financial crimes in complex financial systems more.