Graph-Driven Cross-Industry Real-Time Monitoring Framework for Anti-Money Laundering Detection in Converged Mobility-Energy Supply Chain Networks

2026-05-13

AI Summary

This study addresses the challenge of detecting covert collusive money laundering in cross-industry supply chain finance under scenarios of deep integration between mobility and energy sectors. The authors propose a real-time monitoring approach based on cross-industry heterogeneous graphs, leveraging a temporal dual-graph attention network to dynamically encode fund flow trajectories. A meta-path subgraph reasoning module—integrating contrastive learning with hierarchical graph sampling—is employed to identify collusive fraud structures. To adapt to emerging laundering tactics, a self-supervised online learning mechanism is incorporated. This work pioneers the combination of cross-industry heterogeneous graphs with temporal dual-graph attention mechanisms, achieving an F1-score improvement of over 17.8% compared to existing graph neural networks in real-world deployments, significantly reducing false positives while enhancing both detection capability and real-time adaptability to complex laundering behaviors.

Abstract

With the deep integration of the travel and energy industries, cross-industry supply chain finance has gradually become a high-risk field of hidden money laundering incidents. For this reason, this work proposes a graph-driven cross-industry real-time anti-money laundering monitoring framework (GCRMF) for integrated travel - energy supply chain networks. First, a cross-industry heterogeneous graph (CIHG) covering new energy vehicle rental platforms, energy suppliers, fintech institutions, etc., is constructed, and industry semantics are integrated through temporarily Dual-GAT (Temporal Dual-Graph Attention Network), dynamically encoding capital flow paths and evolution features over time. Subsequently, in order to identify the structural fraud behavior together produced by colluding subjects, a meta-path subgraph reasoning module based on contrastive learning and hierarchical graph sampling is proposed to enhance the discrimination capability of cross-industry recurring money laundering behavior. Meanwhile, a self-supervised online learning mechanism is adopted for real-time adaptation and continuous optimization to new money laundering strategies. The experimental results show that compared with existing graph neural network methods in cross-industry scenarios, GCRMF improves the performance by more than 17.8% of F1 score and greatly reduces the false positive rate.

Problem

• anti-money laundering
• cross-industry
• supply chain finance
• real-time monitoring
• converged mobility-energy networks

Innovation

• Graph Neural Networks
• Cross-Industry Heterogeneous Graph
• Temporal Dual-GAT
• Meta-path Subgraph Reasoning
• Self-supervised Online Learning