Predictive Self-Healing of Financial Trading Microservices Using Spatiotemporal GNNs and DORA-Aligned Evidence Generation
DOI:
https://doi.org/10.63282/3050-9416.IJAIBDCMS-V7I4P103Keywords:
Spatiotemporal Graph Neural Networks, Self-Healing Systems, Failure Propagation, Microservices, Financial Trading Platforms, Chaos Engineering, AIOps, Causal Discovery, Operational Resilience, DORA, Abstention, Automated RemediationAbstract
Financial trading platforms are built from microservices whose failures rarely stay where they start. Degradation in one service travels along call and data dependencies until order handling breaches its service levels. Reactive recovery acts after the breach, and predictive models that watch services one at a time miss propagation that is visible only in the dependency structure. This paper presents a closed-loop resilience controller that integrates four elements. The first is a multi-view service graph that combines dependency, call and telemetry-derived causal-dependency views at the granularity of service instances. The second is a spatiotemporal graph neural network that predicts, for every instance, the probability of a service-level breach within a ten-minute horizon, together with the expected blast radius and the order of propagation. The third is a bounded remediation layer, in which a deterministic safety gate authorizes remediation tiers and enforces market-session constraints, and a supervised action-ranking policy trained from counterfactual replays of chaos scenarios selects among the permitted actions. The fourth is an evidence record designed to align with relevant provisions of the EU Digital Operational Resilience Act (DORA). The controller is evaluated in a simulation-based reference evaluation, a discrete-time simulation of a fourteen-service trading platform with chaos-injected faults, using five fault classes, five severity levels, three workload profiles and thirty repetitions, which gives 2,250 runs per method, split at the scenario level. On held-out test scenarios the proposed model predicted breaches with an F1 of 0.228 (95% CI [0.193, 0.260]) against a base rate of 0.026. It was ahead of a dynamic graph transformer on PR-AUC, of a temporal graph neural network on F1 and of a topology-free baseline on both, and statistically level with a per-instance recurrent model. Removing the recurrent layer reduced F1 by 0.028 (95% CI [0.018, 0.038]). The decisive component was action selection. With predictions held fixed, the learned policy reduced the blast radius by 1.63 instances (95% CI [0.83, 2.50]) and the mean time to recovery by 140 s (95% CI 75 to 213 s) relative to a rule-driven reactive policy, mostly by declining actions that the replays showed to be harmful. The full controller decided in 1.37 ms on average on a laptop CPU. The architecture produces technical evidence aligned with relevant DORA provisions; it does not establish regulatory compliance. All results come from simulation, and evaluation on benchmark deployments and live platforms remains future work.
References
1. European Parliament and Council of the European Union, "Regulation (EU) 2022/2554 of the European Parliament and of the Council of 14 December 2022 on digital operational resilience for the financial sector," Official Journal of the European Union, L 333, pp. 1-79, Dec. 27, 2022. [Online]. Available: https://eur-lex.europa.eu/eli/reg/2022/2554/oj (accessed Oct. 15, 2026).
2. B. Yu, H. Yin, and Z. Zhu, "Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting," in Proc. 27th Int. Joint Conf. Artificial Intelligence (IJCAI), 2018, pp. 3634-3640, doi: 10.24963/ijcai.2018/505.
3. L. Zhao, Y. Song, C. Zhang, Y. Liu, P. Wang, T. Lin, M. Deng, and H. Li, "T-GCN: A temporal graph convolutional network for traffic prediction," IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 9, pp. 3848-3858, 2020, doi: 10.1109/TITS.2019.2935152.
4. L. Wu, J. Tordsson, E. Elmroth, and O. Kao, "MicroRCA: Root cause localization of performance issues in microservices," in Proc. IEEE/IFIP Network Operations and Management Symp. (NOMS), 2020, pp. 1-9, doi: 10.1109/NOMS47738.2020.9110353.
5. J. Soldani and A. Brogi, "Anomaly detection and failure root cause analysis in (micro) service-based cloud applications: A survey," ACM Computing Surveys, vol. 55, no. 3, pp. 1-39, 2022, doi: 10.1145/3501297.
6. J. Kephart and D. Chess, "The vision of autonomic computing," Computer, vol. 36, no. 1, pp. 41-50, 2003, doi: 10.1109/MC.2003.1160055.
7. H. Psaier and S. Dustdar, "A survey on self-healing systems: Approaches and systems," Computing, vol. 91, no. 1, pp. 43-73, 2011, doi: 10.1007/s00607-010-0107-y.
8. S. Uchdadiya, "Deep reinforcement learning for SLA-aware cloud resource management in financial trading platforms," International Journal of Artificial Intelligence and Machine Learning, vol. 6, no. 12s, pp. 332-350, 2026. [Online]. Available: https://www.svedbergopen.com/index.php/ijaiml/article/view/2422 (accessed Oct. 15, 2026).
9. A. Pareja, G. Domeniconi, J. Chen, T. Ma, T. Suzumura, H. Kanezashi, T. Kaler, T. Schardl, and C. Leiserson, "EvolveGCN: Evolving graph convolutional networks for dynamic graphs," in Proc. AAAI Conf. Artificial Intelligence, vol. 34, no. 4, 2020, pp. 5363-5370, doi: 10.1609/aaai.v34i04.5984.
10. L. Yu, L. Sun, B. Du, and W. Lv, "Towards better dynamic graph learning: New architecture and unified library," in Advances in Neural Information Processing Systems, vol. 36, 2023, doi: 10.52202/075280-2960.
11. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, "Graph attention networks," in Proc. Int. Conf. Learning Representations (ICLR), 2018, arXiv:1710.10903.
12. M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling, "Modeling relational data with graph convolutional networks," in The Semantic Web (ESWC 2018), Lecture Notes in Computer Science, Springer, 2018, pp. 593-607, doi: 10.1007/978-3-319-93417-4_38.
13. T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," in Proc. Int. Conf. Learning Representations (ICLR), 2017, arXiv:1609.02907.
14. K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, "Learning phrase representations using RNN encoder-decoder for statistical machine translation," in Proc. 2014 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1724-1734, doi: 10.3115/v1/D14-1179.
15. Y. Gan, Y. Zhang, K. Hu, D. Cheng, Y. He, M. Pancholi, and C. Delimitrou, "Seer: Leveraging big data to navigate the complexity of performance debugging in cloud microservices," in Proc. 24th Int. Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2019, pp. 19-33, doi: 10.1145/3297858.3304004.
16. C. Lee, T. Yang, Z. Chen, Y. Su, and M. R. Lyu, "Eadro: An end-to-end troubleshooting framework for microservices on multi-source data," in Proc. IEEE/ACM 45th Int. Conf. Software Engineering (ICSE), 2023, pp. 1750-1762, doi: 10.1109/ICSE48619.2023.00150.
17. Z. Li, N. Zhao, M. Li, X. Lu, L. Wang, D. Chang, X. Nie, L. Cao, W. Zhang, K. Sui, Y. Wang, X. Du, G. Duan, and D. Pei, "Actionable and interpretable fault localization for recurring failures in online service systems," in Proc. 30th ACM Joint European Software Engineering Conf. and Symp. Foundations of Software Engineering (ESEC/FSE), 2022, pp. 996-1008, doi: 10.1145/3540250.3549092.
18. Y. Gan, M. Liang, S. Dev, D. Lo, and C. Delimitrou, "Sage: Practical and scalable ML-driven performance debugging in microservices," in Proc. 26th ACM Int. Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021, pp. 135-151, doi: 10.1145/3445814.3446700.
19. X. Zhou, X. Peng, T. Xie, J. Sun, C. Ji, W. Li, and D. Ding, "Fault analysis and debugging of microservice systems: Industrial survey, benchmark system, and empirical study," IEEE Transactions on Software Engineering, vol. 47, no. 2, pp. 243-260, 2021, doi: 10.1109/TSE.2018.2887384.
20. T. Ahmed, S. Ghosh, C. Bansal, T. Zimmermann, X. Zhang, and S. Rajmohan, "Recommending root-cause and mitigation steps for cloud incidents using large language models," in Proc. IEEE/ACM 45th Int. Conf. Software Engineering (ICSE), 2023, pp. 1737-1749, doi: 10.1109/ICSE48619.2023.00149.
21. Y. Chen, H. Xie, M. Ma, Y. Kang, X. Gao, L. Shi, Y. Cao, X. Gao, H. Fan, M. Wen, J. Zeng, S. Ghosh, X. Zhang, C. Zhang, Q. Lin, S. Rajmohan, D. Zhang, and T. Xu, "Automatic root cause analysis via large language models for cloud incidents," in Proc. 19th European Conf. Computer Systems (EuroSys), 2024, pp. 674-688, doi: 10.1145/3627703.3629553.
22. P. Notaro, J. Cardoso, and M. Gerndt, "A survey of AIOps methods for failure management," ACM Transactions on Intelligent Systems and Technology, vol. 12, no. 6, pp. 1-45, 2021, doi: 10.1145/3483424.
23. X. Ma, J. Wu, S. Xue, J. Yang, C. Zhou, Q. Z. Sheng, H. Xiong, and L. Akoglu, "A comprehensive survey on graph anomaly detection with deep learning," IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 12, pp. 12012-12038, 2023, doi: 10.1109/TKDE.2021.3118815.
24. P. Spirtes and C. Glymour, "An algorithm for fast recovery of sparse causal graphs," Social Science Computer Review, vol. 9, no. 1, pp. 62-72, 1991, doi: 10.1177/089443939100900106.
25. J. Runge, P. Nowack, M. Kretschmer, S. Flaxman, and D. Sejdinovic, "Detecting and quantifying causal associations in large nonlinear time series datasets," Science Advances, vol. 5, no. 11, Art. no. eaau4996, 2019, doi: 10.1126/sciadv.aau4996.
26. P. Chen, Y. Qi, P. Zheng, and D. Hou, "CauseInfer: Automatic and distributed performance diagnosis with hierarchical causality graph in large distributed systems," in Proc. IEEE INFOCOM, 2014, pp. 1887-1895, doi: 10.1109/INFOCOM.2014.6848128.
27. A. Basiri, N. Behnam, R. de Rooij, L. Hochstein, L. Kosewski, J. Reynolds, and C. Rosenthal, "Chaos engineering," IEEE Software, vol. 33, no. 3, pp. 35-41, 2016, doi: 10.1109/MS.2016.60.
28. A. Basiri, L. Hochstein, N. Jones, and H. Tucker, "Automating chaos experiments in production," in Proc. IEEE/ACM 41st Int. Conf. Software Engineering: Software Engineering in Practice (ICSE-SEIP), 2019, pp. 31-40, doi: 10.1109/ICSE-SEIP.2019.00012.
29. Y. Gan, Y. Zhang, D. Cheng, A. Shetty, P. Rathi, N. Katarki, A. Bruno, J. Hu, B. Ritchken, B. Jackson, K. Hu, M. Pancholi, Y. He, B. Clancy, C. Colen, F. Wen, C. Leung, S. Wang, L. Zaruvinsky, M. Espinosa, R. Lin, Z. Liu, J. Padilla, and C. Delimitrou, "An open-source benchmark suite for microservices and their hardware-software implications for cloud and edge systems," in Proc. 24th Int. Conf. Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2019, pp. 3-18, doi: 10.1145/3297858.3304013.
30. European Commission, "Commission Delegated Regulation (EU) 2024/1772 supplementing Regulation (EU) 2022/2554 with regard to regulatory technical standards specifying the criteria for the classification of ICT-related incidents and cyber threats, setting out materiality thresholds and specifying the details of reports of major incidents," Official Journal of the European Union, 2024. [Online]. Available: https://eur-lex.europa.eu/eli/reg_del/2024/1772/oj (accessed Oct. 15, 2026).
31. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal loss for dense object detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 318-327, 2020, doi: 10.1109/TPAMI.2018.2858826.
32. 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, Art. no. e0118432, 2015, doi: 10.1371/journal.pone.0118432.
33. C. Chow, "On optimum recognition error and reject tradeoff," IEEE Transactions on Information Theory, vol. 16, no. 1, pp. 41-46, 1970, doi: 10.1109/TIT.1970.1054406.
