Artificial Intelligence-Driven Fraud Detection at Scale: A Novel Deep Advanced Deep Learning Model for Protecting High-Volume Instant Payment Networks

Abstract

The rapid growth of instant payments and card-not-present transactions has created an urgent need for effective real-time fraud detection. Conventional rule-based systems and basic machine learning models face significant limitations, including weak adaptability to concept drift, restricted ability to recognize complex fraud patterns, and difficulties in scaling to massive transaction volumes. These challenges arise largely from their dependence on fixed, manually engineered features and an inability to capture sophisticated temporal relationships within transaction sequences. To address these shortcomings, this study introduces the Temporal Graph Attention Network with Anomaly-aware Embeddings (TGAT-AAE), an advanced deep learning framework for scalable and adaptive fraud detection. The model integrates three key innovations: a dynamic temporal graph structure that preserves sequential transaction information, an anomaly-aware embedding component based on contrastive learning for strong representations in imbalanced datasets, and a multi-head temporal attention mechanism that concentrates on suspicious sub-graphs to improve detection accuracy. Experimental evaluations on the IEEE-CIS fraud detection benchmark and a proprietary dataset with over 50 million transactions demonstrate that TGAT-AAE achieves superior performance, surpassing baseline models by 12–18% while maintaining inference times below 10 milliseconds. The model shows strong robustness to concept drift and supports horizontal scalability for processing millions of transactions per second. By combining self-supervised learning with graph-based temporal modeling, TGAT-AAE effectively addresses class imbalance and enables continuous learning from streaming financial data, thereby reducing the necessity for frequent retraining. This provides financial institutions with a practical and scalable solution for strengthening payment security against increasingly sophisticated cyber threats, while future research may explore federated learning for privacy-preserving collaboration across distributed banking systems.

References

Ahmed, A., Rahman, S., Islam, M., Chowdhury, F., & Badhan, I. A. (2023). Challenges and opportunities in implementing machine learning for healthcare supply chain optimization: A data-driven examination. International journal of business and management sciences, 3(07), 6-31.

Asif, M., Pasha, M. A., Mumtaz, A., & Sabir, B. (2023). Causes of youth unemployment in Pakistan. Inverge Journal of Social Sciences, 2(1), 41–50. https://doi.org/10.63544/ijss.v2i1.21

Asif, M., & Shaheen, A. (2022). Creating a high-performance workplace by the determination of importance of job satisfaction, employee engagement, and leadership. Journal of Business Insight and Innovation, 1(2), 9–15.

Aurangzeb, Asif, M., & Amin, M. K. (2021). Resources Management and SME’s Performance. Humanities & Social Sciences Reviews, 9(3), 679–689. https://doi.org/10.18510/hssr.2021.9367

Badhan, I. A., Hasnain, M. N., & Rahman, M. H. (2022). Enhancing Operational Efficiency: A Comprehensive Analysis of Machine Learning Integration in Industrial Automation. Journal of Business Insight and Innovation, 1(2), 61-77.

Bank for International Settlements. (2022). Annual economic report 2022: The future of the monetary system. BIS Publications. https://www.bis.org/publ/arpdf/ar2022e.htm

Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. C. (2011). Data mining for credit card fraud: A comparative study. Decision Support Systems, 50(3), 602–613. https://doi.org/10.1016/j.dss.2010.08.008

Bogen, M., Rieke, A., & Ahmed, S. (2022). Awareness in practice: Tensions in access to sensitive attribute data for antidiscrimination. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (pp. 1803–1815). Association for Computing Machinery. https://doi.org/10.1145/3531146.3533139

Bose, A., Bhattacharjee, K., & Roy, S. (2022). Adversarial attacks on graph neural networks for fraud detection: A comprehensive survey. ACM Computing Surveys, 55(4), Article 78, 1–38. https://doi.org/10.1145/3511808

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785

Chen, Y., Wang, X., & Zhang, L. (2021). Real-time fraud detection in payment networks: Challenges and opportunities. IEEE Transactions on Knowledge and Data Engineering, 33(8), 3127–3142. https://doi.org/10.1109/TKDE.2020.2975623

Choain, A. H. K., Majumder, C., Nasir, M. A. N., & Sultana, N. (2023). Integrating blockchain-enhanced enterprise systems for US banking, pharmaceutical supply chains, economic resilience, and secure operational models. Journal of Engineering and Computational Intelligence Review, 1(1), 51-63.

Dal Pozzolo, A., Caelen, O., Johnson, R. A., & Bontempi, G. (2015). Calibrating probability with undersampling for unbalanced classification. In Proceedings of the 2015 IEEE Symposium Series on Computational Intelligence (pp. 159–166). IEEE. https://doi.org/10.1109/SSCI.2015.33

Davis, J., & Goadrich, M. (2006). The relationship between precision-recall and ROC curves. In Proceedings of the 23rd International Conference on Machine Learning (pp. 233–240). Association for Computing Machinery. https://doi.org/10.1145/1143844.1143874

Deloitte. (2023). Global risk management survey: Financial services industry outlook. Deloitte Insights. https://www2.deloitte.com/global/en/insights/topics/risk-management.html

European Commission. (2023). Regulation (EU) 2023/1114 of the European Parliament and of the Council on artificial intelligence (AI Act). Official Journal of the European Union. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32023R1114

Fey, M., & Lenssen, J. E. (2019). Fast graph representation learning with PyTorch Geometric. In ICLR Workshop on Representation Learning on Graphs and Manifolds. https://arxiv.org/abs/1903.02428

FICO. (2023). FICO global fraud report: Payment fraud trends and countermeasures. FICO Analytics. https://www.fico.com/en/latest-thinking/report/global-fraud-report-2023

Fiore, U., De Santis, A., Perla, F., Zanetti, P., & Palmieri, F. (2019). Using generative adversarial networks for improving classification effectiveness in credit card fraud detection. Information Sciences, 479, 448–455. https://doi.org/10.1016/j.ins.2017.12.030

Goyal, P., & Ferrara, E. (2023). Graph neural networks for fraud detection: A comprehensive review. ACM Transactions on Intelligent Systems and Technology, 14(2), Article 32, 1–35. https://doi.org/10.1145/3570507

Hamilton, W. L., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems 30 (pp. 1024–1034). Curran Associates. https://proceedings.neurips.cc/paper/2017/file/5dd9db5e033da9c6fb5ba83c7a7ebea9-Paper.pdf

IEEE-CIS. (2019). IEEE-CIS fraud detection dataset [Data set]. Kaggle. https://www.kaggle.com/c/ieee-fraud-detection

Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P. E., He-Guelton, L., & Caelen, O. (2018). Sequence classification for credit-card fraud detection. Expert Systems with Applications, 100, 234–245. https://doi.org/10.1016/j.eswa.2018.01.037

Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., ... & Zhao, S. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210. https://doi.org/10.1561/2200000083

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30 (pp. 3146–3154). Curran Associates. https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf

Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations. https://arxiv.org/abs/1609.02907

Kumar, S., Zhang, X., & Leskovec, J. (2022). Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1269–1278). Association for Computing Machinery. https://doi.org/10.1145/3534678.3539102

Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2020). Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2), 318–327. https://doi.org/10.1109/TPAMI.2018.2858826

Liu, Z., Chen, C., Yang, X., Zhou, J., Li, X., & Song, L. (2018). Heterogeneous graph neural networks for malicious account detection. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (pp. 2077–2085). Association for Computing Machinery. https://doi.org/10.1145/3269206.3272010

Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In Proceedings of the 7th International Conference on Learning Representations. https://arxiv.org/abs/1711.05101

Ma, Y., Guo, Z., Ren, Z., Tang, J., & Yin, D. (2020). Streaming graph neural networks. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 719–728). Association for Computing Machinery. https://doi.org/10.1145/3397271.3401092

McKinsey & Company. (2023). The 2023 McKinsey global payments report. McKinsey & Company Financial Services. https://www.mckinsey.com/industries/financial-services/our-insights/global-payments-report

McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (pp. 1273–1282). PMLR. https://proceedings.mlr.press/v54/mcmahan17a.html

Nazir, Q. U. A. (2023). AI-powered radiology: Innovations and challenges in medical imaging. Journal of Engineering and Computational Intelligence Review, 1(1), 7-13.

Nilson Report. (2024). Global card fraud losses. Nilson Report, Issue 1254. https://nilsonreport.com/mention/1254/1link/

Pang, G., Shen, C., Cao, L., & Hengel, A. V. D. (2021). Deep learning for anomaly detection: A review. ACM Computing Surveys, 54(2), Article 38, 1–38. https://doi.org/10.1145/3439950

Poursafaei, F., Huang, S., Pelrine, K., & Rabbany, R. (2022). Towards better evaluation for dynamic link prediction. In Advances in Neural Information Processing Systems 35 (pp. 32928–32941). Curran Associates. https://proceedings.neurips.cc/paper_files/paper/2022/file/d49042a5d49818711c401d34172f9900-Paper-Datasets_and_Benchmarks.pdf

Pumsirirat, A., & Yan, L. (2020). Credit card fraud detection using deep learning based on auto-encoder and restricted Boltzmann machine. International Journal of Advanced Computer Science and Applications, 9(1), 18–25. https://doi.org/10.14569/IJACSA.2018.090103

Rodriguez, M., & Liu, H. (2023). Adaptive machine learning for evolving fraud patterns in digital payments. Journal of Financial Technology, 5(2), 112–134. https://doi.org/10.1016/j.jfintech.2023.100089

Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., & Bronstein, M. (2020). Temporal graph networks for deep learning on dynamic graphs. In ICML 2020 Workshop on Graph Representation Learning. https://arxiv.org/abs/2006.10637

Roy, A., Sun, J., Mahoney, R., Alonzi, L., Adams, S., & Beling, P. (2018). Deep learning detecting fraud in credit card transactions. In Proceedings of the 2018 Systems and Information Engineering Design Symposium (pp. 129–134). IEEE. https://doi.org/10.1109/SIEDS.2018.8374722

Saito, T., & Rehmsmeier, M. (2021). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3), Article e0118432. https://doi.org/10.1371/journal.pone.0118432

Shi, L., Wu, L., Ying, X., & Wu, X. (2022). Integrating threat intelligence for real-time fraud detection. IEEE Transactions on Dependable and Secure Computing, 19(4), 2534–2548. https://doi.org/10.1109/TDSC.2021.3089145

Shiva, T. A., Brown, J. G., McField, A. A., Osborne, R. E., & Oberle, C. D. (2024). Cultural associations with prosocial behaviors and attitudes among Asian Americans. Asian American Journal of Psychology, 16(3), 268–278. https://doi.org/10.1037/aap0000368

Shiva, T. A., Ireen, N., & Islam, M. S. (2024). Optimizing early intervention strategies for neurodiverse children (ASD): Reducing long-term public healthcare costs through parent-mediated training. Apex Journal of Social Sciences, 3(1), 30–52. https://apexjss.com/index.php/AJSS/article/view/18

Statista. (2023). Digital payments worldwide: Statistics and market data. Statista Research Department. https://www.statista.com/outlook/dmo/fintech/digital-payments/worldwide

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems 30 (pp. 5998–6008). Curran Associates. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf

Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations. https://arxiv.org/abs/1710.10903

Wang, D., Lin, J., Cui, P., Jia, Q., Wang, Z., Fang, Y., ... & Zhu, W. (2019). A semi-supervised graph attentive network for financial fraud detection. In Proceedings of the 2019 IEEE International Conference on Data Mining (pp. 598–607). IEEE. https://doi.org/10.1109/ICDM.2019.00070

Wang, M., Zheng, D., Ye, Z., Gan, Q., Li, M., Song, X., ... & Zhang, Z. (2020). Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv preprint. https://arxiv.org/abs/1909.01315

Wang, X., Liu, Y., Zhang, C., & Yu, P. S. (2021). Heterogeneous graph attention network for fraud detection. In Proceedings of the Web Conference 2021 (pp. 1953–1964). Association for Computing Machinery. https://doi.org/10.1145/3442381.3449786

Weber, M., Domeniconi, G., Chen, J., Weidele, D. K. I., Bellei, C., Robinson, T., & Leiserson, C. E. (2019). Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. In KDD 2019 Workshop on Anomaly Detection in Finance. https://arxiv.org/abs/1908.02591

Weinberger, K., Dasgupta, A., Langford, J., Smola, A., & Attenberg, J. (2009). Feature hashing for large scale multitask learning. In Proceedings of the 26th Annual International Conference on Machine Learning (pp. 1113–1120). Association for Computing Machinery. https://doi.org/10.1145/1553374.1553516

Whitrow, C., Hand, D. J., Juszczak, P., Weston, D., & Adams, N. M. (2020). Transaction aggregation as a strategy for credit card fraud detection. Data Mining and Knowledge Discovery, 18(1), 30–55. https://doi.org/10.1007/s10618-008-0116-z

Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., & Achan, K. (2020). Inductive representation learning on temporal graphs. In Proceedings of the 8th International Conference on Learning Representations. https://arxiv.org/abs/2002.07962

Ying, R., Bourgeois, D., You, J., Zitnik, M., & Leskovec, J. (2019). GNNExplainer: Generating explanations for graph neural networks. In Advances in Neural Information Processing Systems 32 (pp. 9244–9255). Curran Associates. https://proceedings.neurips.cc/paper/2019/file/d80b7040b773199015de6d3b4293c8ff-Paper.pdf

Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018). Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 974–983). Association for Computing Machinery. https://doi.org/10.1145/3219819.3219890

Yoon, J., Jordon, J., & Van Der Schaar, M. (2018). GAIN: Missing data imputation using generative adversarial nets. In Proceedings of the 35th International Conference on Machine Learning (pp. 5689–5698). PMLR. https://proceedings.mlr.press/v80/yoon18a.html

Zeng, H., Zhou, H., Srivastava, A., Kanber, R., Prasad, M., & Hu, X. (2021). GraphSAINT: Graph sampling based inductive learning method. In Proceedings of the 9th International Conference on Learning Representations. https://arxiv.org/abs/1907.04931

Zhang, B. H., Lemoine, B., & Mitchell, M. (2018). Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society (pp. 335–340). Association for Computing Machinery. https://doi.org/10.1145/3278721.3278779

Zhang, Y., Liu, Q., & Wu, L. (2020). Neural network-based credit card fraud detection with feature engineering. IEEE Access, 8, 158275–158287. https://doi.org/10.1109/ACCESS.2020.3019867

Zheng, P., Yuan, S., Wu, X., Li, J., & Lu, A. (2022). Adversarial fraud detection: A survey of attacks and defenses. ACM Computing Surveys, 54(8), Article 167, 1–36. https://doi.org/10.1145/3466772