🤖 AI Summary
To address critical challenges in financial fraud detection—including extreme label imbalance, stealthy fraudulent behaviors, dilution of central-node information by neighboring nodes, and dynamic evolution of graph structures—this paper proposes RL-GNN, a reinforcement learning–guided graph neural network framework for joint dynamic modeling. The method innovatively introduces (i) a policy network to steer subgraph exploration toward suspicious regions, (ii) a center-neighborhood gated fusion module to preserve discriminative node representations, and (iii) a learnable temporal edge update mechanism to capture evolving transaction patterns. It integrates Graph Attention Networks (GATs), Proximal Policy Optimization (PPO)-based reinforcement learning, and adaptive neighbor sampling. Evaluated on three real-world financial transaction datasets, RL-GNN achieves absolute improvements of 12.7% in F1-score and 9.3% in AUC over prior state-of-the-art methods; notably, it attains 78.5% accuracy in zero-shot fraud identification—demonstrating superior generalization to unseen fraud types.
📝 Abstract
Financial fraud refers to the act of obtaining financial benefits through dishonest means. Such behavior not only disrupts the order of the financial market but also harms economic and social development and breeds other illegal and criminal activities. With the popularization of the internet and online payment methods, many fraudulent activities and money laundering behaviors in life have shifted from offline to online, posing a great challenge to regulatory authorities. How to efficiently detect these financial fraud activities has become an urgent issue that needs to be resolved. Graph neural networks are a type of deep learning model that can utilize the interactive relationships within graph structures, and they have been widely applied in the field of fraud detection. However, there are still some issues. First, fraudulent activities only account for a very small part of transaction transfers, leading to an inevitable problem of label imbalance in fraud detection. At the same time, fraudsters often disguise their behavior, which can have a negative impact on the final prediction results. In addition, existing research has overlooked the importance of balancing neighbor information and central node information. For example, when the central node has too many neighbors, the features of the central node itself are often neglected. Finally, fraud activities and patterns are constantly changing over time, so considering the dynamic evolution of graph edge relationships is also very important.