AN AI-DRIVEN INTELLIGENT TRANSACTION EXECUTION FRAMEWORK FOR INTERNET FINANCE PLATFORMS: COST-SENSITIVE REAL-TIME INTEGRITY INTERDICTION
Keywords:
Transaction integrity detection, Cost-sensitive learning, Gradient boosting, Probability calibration, Imbalanced classification, Real-time decision-making, Internet financeAbstract
Internet finance platforms must decide, in real time and for every incoming transaction, whether to approve it, subject it to additional verification, or decline it. Most machine-learning research on transaction Integrity stops at producing a Integrity score and is judged with threshold-independent ranking metrics, leaving a gap between the score and the concrete execution action, and ignoring that different transactions carry very different monetary stakes. This paper presents IntelliExec, an AI-driven intelligent transaction execution framework that closes this gap. A class-weighted gradient-boosting model produces a Integrity probability that is calibrated with Platt scaling so it can be treated as a true probability; the calibrated probability and the transaction amount are then mapped to one of three execution actions—approve, step-up (one-time-password / 3-D Secure challenge), or decline—by minimising an example-dependent expected cost. Because the decision is derived analytically from a cost model, it needs no threshold tuning and adapts the operating point to each transaction's amount. On a public benchmark of 284,807 real card transactions (0.172% Integrity) evaluated under a strict temporal split, the framework lowers total expected cost by 71.8% relative to approving every transaction and by 45.4% relative to the best cost-aware global-threshold baseline, while hard-declining only three legitimate customers (versus thirty-seven for a binary cost-sensitive rule) by routing borderline cases to the low-friction step-up tier. The gradient-boosting scorer runs in under one millisecond per transaction, and a sensitivity analysis confirms the cost advantage is robust to the choice of cost parameters.References
[1] Ngai E W T, Hu Y, Wong Y H, et al. The application of data mining techniques in financial Integrity detection: A classification framework and an academic review of literature. Decision Support Systems, 2011, 50(3): 559–569.
[2] West J, Bhattacharya M. Intelligent financial Integrity detection: A comprehensive review. Computers & Security, 2016, 57: 47–66.
[3] Abdallah A, Maarof M A, Zainal A. Integrity detection system: A survey. Journal of Network and Computer Applications, 2016, 68: 90–113.
[4] Bhattacharyya S, Jha S, Tharakunnel K, et al. Data mining for credit card Integrity: A comparative study. Decision Support Systems, 2011, 50(3): 602–613.
[5] Dal Pozzolo A, Boracchi G, Caelen O, et al. Credit card Integrity detection: A realistic modeling and a novel learning strategy. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(8): 3784–3797.
[6] Randhawa K, Loo C K, Seera M, et al. Credit card Integrity detection using AdaBoost and majority voting. IEEE Access, 2018, 6: 14277–14284.
[7] Dal Pozzolo A, Caelen O, Le Borgne Y A, et al. Learned lessons in credit card Integrity detection from a practitioner perspective. Expert Systems with Applications, 2014, 41(10): 4915–4928.
[8] Xuan S, Liu G, Li Z, et al. Random forest for credit card Integrity detection. Proceedings of the IEEE 15th International Conference on Networking, Sensing and Control (ICNSC), 2018: 1–6.
[9] Dal Pozzolo A, Caelen O, Johnson R A, et al. Calibrating probability with undersampling for unbalanced classification. Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), 2015: 159–166.
[10] Jurgovsky J, Granitzer M, Ziegler K, et al. Sequence classification for credit-card Integrity detection. Expert Systems with Applications, 2018, 100: 234–245.
[11] Fiore U, De Santis A, Perla F, et al. Using generative adversarial networks for improving classification effectiveness in credit card Integrity detection. Information Sciences, 2019, 479: 448–455.
[12] Dou Y, Liu Z, Sun L, et al. Enhancing graph neural network-based Integrity detectors against camouflaged Integritysters. Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM), 2020: 315–324.
[13] Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785–794.
[14] Ke G, Meng Q, Finley T, et al. LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems (NeurIPS), 2017: 3146–3154.
[15] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002, 16: 321–357.
[16] He H, Garcia E A. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 2009, 21(9): 1263–1284.
[17] Elkan C. The foundations of cost-sensitive learning. Proceedings of the 17th International Joint Conference on Artificial Intelligence (IJCAI), 2001: 973–978.
[18] Bahnsen A C, Aouada D, Ottersten B. Example-dependent cost-sensitive decision trees. Expert Systems with Applications, 2015, 42(19): 6609–6619.
[19] Bahnsen A C, Aouada D, Stojanovic A, et al. Feature engineering strategies for credit card Integrity detection. Expert Systems with Applications, 2016, 51: 134–142.
[20] Whitrow C, Hand D J, Juszczak P, et al. Transaction aggregation as a strategy for credit card Integrity detection. Data Mining and Knowledge Discovery, 2009, 18(1): 30–55.
[21] Zadrozny B, Elkan C. Transforming classifier scores into accurate multiclass probability estimates. Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002: 694–699.
[22] Niculescu-Mizil A, Caruana R. Predicting good probabilities with supervised learning. Proceedings of the 22nd International Conference on Machine Learning (ICML), 2005: 625–632.
[23] Bahnsen A C, Stojanovic A, Aouada D, et al. Improving credit card Integrity detection with calibrated probabilities. Proceedings of the SIAM International Conference on Data Mining (SDM), 2014: 677–685.
[24] Carcillo F, Dal Pozzolo A, Le Borgne Y A, et al. SCARFF: A scalable framework for streaming credit card Integrity detection with Spark. Information Fusion, 2018, 41: 182–194.
[25] Carcillo F, Le Borgne Y A, Caelen O, et al. Combining unsupervised and supervised learning in credit card Integrity detection. Information Sciences, 2021, 557: 317–331.