AI-Driven KYC Optimization Using Graph Neural Networks
Keywords:
Graph Neural Networks, Know Your Customer, Financial Compliance, Anti-Money Laundering, Fraud DetectionAbstract
Graph-based learning revolutionized KYC financial compliance. GNNs might change global KYC. Clients, transactions, and intermediaries are heterogeneous network nodes and edges in GNNs, exposing fraud rings, synthetic identities, and financial collaboration. GNN KYC models match Random Forests and SVMs in accuracy, recall, F1-score, and computation. Automation satisfies worldwide AML criteria after FATF compliance review. Geographical networks improve due diligence, client risk assessment, and onboarding by surpassing standard models in accuracy and relationship inference. We found that GNN-driven solutions improved banking institution KYC systems and operations.
Downloads
References
J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, and M. Sun, "Graph Neural Networks: A Review of Methods and Applications," AI Open, vol. 1, no. 1, pp. 57–81, 2020.
S. Motie and M. Raahemi, "Financial Fraud Detection Using Graph Neural Networks," Computers, Materials & Continua, vol. 70, no. 2, pp. 2293–2311, 2024.
Y. Zhang, "A Graph Neural Network-Based Approach for Detecting Fraud in Digital Accounting Systems," Asian Journal of Science and Management, vol. 2, no. 6, pp. 1–15, 2024.
M. Rahmati, "Real-Time Financial Fraud Detection Using Adaptive Graph Neural Networks and Federated Learning," International Journal of Management and Data Analytics, vol. 5, no. 1, pp. 98–110, 2025.
F. Xu et al., "Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum," arXiv preprint arXiv:2312.06441, 2023.
M. Lu et al., "BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection," arXiv preprint arXiv:2205.13084, 2022.
Y. Zhang, "Graph Neural Network for Customer Engagement in Digital Banking," University of Hawaii ScholarSpace, 2024.
K. Khanvilkar and K. Kommuru, "Regulatory Graphs and GenAI for Real-Time Transaction Monitoring and Compliance Explanation in Banking," arXiv preprint arXiv:2506.01093, 2025.
Q. Sha et al., "Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention," arXiv preprint arXiv:2504.08183, 2025.
S. Motie and M. Raahemi, "A Review on Graph Neural Network Methods in Financial Fraud Detection," Journal of Data Science, vol. 20, no. 1, pp. 1–20, 2022.
Y. Dai et al., "A Comprehensive Survey on Trustworthy Graph Neural Networks," Journal of Computer Science and Technology, vol. 39, no. 1, pp. 1–25, 2024.
M. Rahmati, "Real-Time Financial Fraud Detection Using Adaptive Graph Neural Networks and Federated Learning," ResearchGate, 2025.
S. Motie and M. Raahemi, "Financial Fraud Detection Using Graph Neural Networks," ScienceDirect, 2024.
F. Xu et al., "Revisiting Graph-Based Fraud Detection in Sight of Heterophily and Spectrum," arXiv, 2023.
M. Lu et al., "BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection," arXiv, 2022.
Y. Zhang, "Graph Neural Network for Customer Engagement in Digital Banking," University of Hawaii ScholarSpace, 2024.
K. Khanvilkar and K. Kommuru, "Regulatory Graphs and GenAI for Real-Time Transaction Monitoring and Compliance Explanation in Banking," arXiv, 2025.
Q. Sha et al., "Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention," arXiv, 2025.
S. Motie and M. Raahemi, "A Review on Graph Neural Network Methods in Financial Fraud Detection," Journal of Data Science, 2022.
Y. Dai et al., "A Comprehensive Survey on Trustworthy Graph Neural Networks," Journal of Computer Science and Technology, 2024.
