Agentic Payment Risk Orchestration: Adaptive Multi-Vendor Decision-Making Under Risk, Latency, and Cost Constraints
DOI:
https://doi.org/10.29284/2v3ene19Keywords:
payment fraud; agentic AI; risk orchestration; offline reinforcement learning; constrained MDP; cost-sensitive learning; adaptive screening; fraud detectionAbstract
Payment-risk systems typically optimize fraud scores while treating external-service routing, computational effort, and operational conditions as separate concerns. This study introduces Agentic Payment Risk Orchestration (APRO), a transaction-level sequential decision framework that selects among internal models and external risk services while jointly accounting for fraud exposure, false declines, latency, vendor cost, and runtime service state. The orchestration problem is formulated as a constrained Markov decision process in which the policy may request additional evidence or terminate with approve, decline, or review. Across six evaluated strategies, APRO achieved 95.6% fraud recall, 93.7% precision, PR-AUC of 0.968, ROC-AUC of 0.979, a 2.1% false-decline rate, 91 ms mean latency, 173 ms P95 latency, 0.91 vendor calls per transaction, and risk-adjusted utility of 0.93. Compared with the risk-only learned policy, APRO reduced total risk-adjusted cost by 16.7%; relative to exhaustive all-checks, the reduction was 24.7%. Stress tests showed that APRO retained the highest utility under doubled fraud prevalence, vendor latency degradation, vendor outage, cost inflation, distribution shift, and a high-value traffic surge. Ablation results further showed that learned stopping and operational-state awareness materially contributed to the latency-cost-risk trade-off. The findings support sequential, context-sensitive evidence acquisition as a practical alternative to uniform or statically cascaded payment screening.
References
[1] S. Bhattacharyya, S. Jha, K. Tharakunnel, and J. C. Westland, “Data mining for credit card fraud: A comparative study,” Decision Support Systems, vol. 50, no. 3, pp. 602–613, 2011.
[2] A. C. Bahnsen, D. Aouada, A. Stojanovic, and B. Ottersten, “Feature engineering strategies for credit card fraud detection,” Expert Systems with Applications, vol. 51, pp. 134–142, 2016.
[3] A. Dal Pozzolo, G. Boracchi, O. Caelen, C. Alippi, and G. Bontempi, “Credit card fraud detection: A realistic modeling and a novel learning strategy,” IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 8, pp. 3784–3797, 2018.
[4] F. Carcillo, A. Dal Pozzolo, Y.-A. Le Borgne, O. Caelen, Y. Mazzer, and G. Bontempi, “Scarff: A scalable framework for streaming credit card fraud detection with Spark,” Information Fusion, vol. 41, pp. 182–194, 2018.
[5] Y.-A. Le Borgne, W. Siblini, B. Lebichot, and G. Bontempi, Reproducible Machine Learning for Credit Card Fraud Detection: Practical Handbook. Université Libre de Bruxelles, 2022.
[6] V. Van Vlasselaer, C. Bravo, O. Caelen, T. Eliassi-Rad, L. Akoglu, M. Snoeck, and B. Baesens, “APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions,” Decision Support Systems, vol. 75, pp. 38–48, 2015.
[7] A. C. Bahnsen, A. Stojanovic, D. Aouada, and B. Ottersten, “Cost sensitive credit card fraud detection using Bayes minimum risk,” in 2013 12th International Conference on Machine Learning and Applications, 2013, pp. 333–338.
[8] J. J. West and M. Bhattacharya, “Intelligent financial fraud detection: A comprehensive review,” Computers & Security, vol. 57, pp. 47–66, 2016.
[9] S. Ryman-Tubb, P. Krause, and W. Garn, “How Artificial Intelligence and machine learning research impacts payment card fraud detection: A survey and industry benchmark,” Engineering Applications of Artificial Intelligence, vol. 76, pp. 130–157, 2018.
[10] K. Ghosh Dastidar, O. Caelen, and M. Granitzer, “Machine learning methods for credit card fraud detection: A survey,” IEEE Access, vol. 12, pp. 158939–158965, 2024.
[11] M. L. Puterman, Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, 1994.
[12] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. MIT Press, 2018.
[13] V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
[14] J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P. Moritz, “Trust region policy optimization,” in Proc. ICML, 2015, pp. 1889–1897.
[15] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv:1707.06347, 2017.
[16] J. Achiam, D. Held, A. Tamar, and P. Abbeel, “Constrained policy optimization,” in Proc. 34th International Conference on Machine Learning, PMLR 70, 2017, pp. 22–31.
[17] S. Levine, A. Kumar, G. Tucker, and J. Fu, “Offline reinforcement learning: Tutorial, review, and perspectives on open problems,” arXiv:2005.01643, 2020.
[18] R. F. Prudencio, M. R. O. A. Maximo, and E. L. Colombini, “A survey on offline reinforcement learning: Taxonomy, review, and open problems,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
[19] T. Saito and M. Rehmsmeier, “The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets,” PLoS ONE, vol. 10, no. 3, e0118432, 2015.
[20] Q. McNemar, “Note on the sampling error of the difference between correlated proportions or percentages,” Psychometrika, vol. 12, pp. 153–157, 1947.
[21] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002.
[22] H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263–1284, 2009.
[23] J. Gama, I. Žliobaitė, A. Bifet, M. Pechenizkiy, and A. Bouchachia, “A survey on concept drift adaptation,” ACM Computing Surveys, vol. 46, no. 4, art. 44, 2014.
[24] G. Widmer and M. Kubat, “Learning in the presence of concept drift and hidden contexts,” Machine Learning, vol. 23, pp. 69–101, 1996.
[25] A. Bifet and R. Gavaldà, “Learning from time-changing data with adaptive windowing,” in Proc. SIAM International Conference on Data Mining, 2007, pp. 443–448.
[26] L. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5–32, 2001.
[27] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
[28] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems 30, 2017, pp. 3146–3154.
[29] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[30] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. ICLR, 2015.
[31] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006.
[32] A. Niculescu-Mizil and R. Caruana, “Predicting good probabilities with supervised learning,” in Proc. 22nd International Conference on Machine Learning, 2005, pp. 625–632.
[33] G. W. Brier, “Verification of forecasts expressed in terms of probability,” Monthly Weather Review, vol. 78, no. 1, pp. 1–3, 1950.
[34] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems 30, 2017, pp. 4765–4774.
[35] A. Hernandez Aros, L. X. Bustamante Molano, F. Gutierrez-Portela, J. J. Moreno Hernandez, and M. S. Rodríguez Barrero, “Financial fraud detection through the application of machine learning techniques: A literature review,” Humanities and Social Sciences Communications, vol. 11, art. 1130, 2024.
[36] Suneeth and Kamal, “Dynamic telemetry orchestration and signal elevation: An edge-native AI proxy architecture for industrial cyber-physical systems,” Oct. 2023, doi: 10.64882/ijrt.v11.i4.1097.
[37] Sheetal, Himant, and Prabhav, “Multi-agent automated feature engineering for high-dimensional big data,” Dec. 2023. [Online]. Available: https://ijrt.org/j/article/view/1128.
[38] Soumya and Nikhil, “AI-powered cost optimization in IoT: A systematic review of machine learning and predictive analytics in TCO reduction,” Dec. 2024.
[39] Ankush, “Financial risk prediction through multivariate data analytics and ensemble learning,” Dec. 2024. [Online]. Available: https://romanpub.com/resources/smc-v4-2-2024-3.pdf.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
