Design of a financial fraud detection model optimized by multi-task learning and graph neural networks
Abstract
Contemporary financial regulation and risk identification are increasingly challenged by the escalating intricacy of inter-firm relational architectures, the diversification of financial conduct, and the multidimensionality of data sources. Conventional fraud detection methodologies, predominantly grounded in single-task paradigms and static heuristic indicators, are insufficient to holistically capture the complex manifestations of fraudulent corporate behavior, encompassing both financial anomalies and behavioral aberrations. To surmount these limitations, this study introduces GN-MTNet, a novel financial fraud detection framework that synthesizes graph neural networks with multi-task learning. The proposed architecture constructs enterprise relational graphs, employs graph-based neural encoders to extract high-order structural representations, and concurrently addresses three core tasks: fraud identification, anomaly quantification, and behavioral deviation classification. A unified, shared multi-task learning framework is devised to encapsulate firm-level irregularities from diverse analytical perspectives, thereby facilitating the synergistic optimization of risk detection and pattern discernment. Empirical evaluations conducted on two benchmark datasets—the Financial Statement Fraud Dataset and OpenCorporates+AMiner—demonstrate that GN-MTNet markedly surpasses existing approaches in terms of classification precision, anomaly reconstruction capability, and multi-task synergy. Ablation studies further substantiate the critical contributions of graph-based modeling, the task-sharing mechanism, and the composite loss formulation to the model’s holistic efficacy. Collectively, this methodology offers a more nuanced and intelligent paradigm for financial fraud detection, furnishing essential technical underpinnings for the development of enterprise risk profiling and the enhancement of intelligent financial auditing systems.