Explainable AI anomaly Detection in Banking Microservices
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V5I2P123Keywords:
Explainable Artificial Intelligence, Anomaly Detection, Banking Microservices, Machine Learning, Distributed Systems, Financial Cybersecurity, Service MonitoringAbstract
In a move to offer real time, resilient and scalable banking services, banks are also resorting to distributed microservice-based banking applications. The dynamics of interactions among microservices however create heterogeneous logs, metrics, traces, and transaction events, and it is challenging to detect and interpret anomalous behavior in a timely manner. Traditional approaches to anomaly detection are useful at pointing out anomalies in system behavior, but tend to give few attempts to explain why they made their predictions, diminishing its value to security analysts and banking operations staff teams. The present paper will present an explainable AI (XAI) architecture of banking microservices based anomaly detection that will possess such modules as the behavioral monitoring module, multi-source telemetry analysis module, anomaly detection by machine learning and explanation module. The framework will associate service-level and transaction-level metrics with each other to differentiate regular service variation with operations and instances of suspicious or abnormal behavior. Mechanisms of explainability would provide evidence of the characteristics and service engagement and patterns of behavior that have resulted in each anomaly decision that are interpretable. The solution will be to enhance the quality of anomaly detection, transparency of diagnosis, and analyst confidence and aid in timely responding to incidents in diverse banking settings. The systematic basis of reliable AI-assisted monitoring of distributed financial services would be offered through its scalability, interpretability, and applicability to operations as also brought out in the framework.
References
[1] Aguilar, D. L., Medina Perez, M. A., Loyola-Gonzalez, O., Choo, K.-K. R., & Bucheli-Susarrey, E. (2023). Towards an interpretable autoencoder: A decision tree-based autoencoder and its application in anomaly detection. IEEE Transactions on Dependable and Secure Computing, 20(2), 1048–1049.
[2] Ahmed, M., Mahmood, A. N., & Islam, M. R. (2016). A survey of anomaly detection techniques in financial domain. Future Generation Computer Systems, 55, 278–288.
[3] Antwarg, L., Miller, R. M., Shapira, B., & Rokach, L. (2021). Explaining anomalies detected by autoencoders using Shapley additive explanations. Expert Systems with Applications, 186, 115736.
[4] Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., Raja, C., & Herrera, F. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.
[5] Barbado, A., Corcho, Ó., & Benjamins, R. (2022). Rule extraction in unsupervised anomaly detection for model explainability: Application to One-Class SVM. Expert Systems with Applications, 189, 116100.
[6] Carletti, M., Terzi, M., & Susto, G. A. (2023). Interpretable anomaly detection with DiFFI: Depth-based feature importance of isolation forest. Engineering Applications of Artificial Intelligence, 119, 105730.
[7] Böhmer, K., & Rinderle-Ma, S. (2020). Mining association rules for anomaly detection in dynamic process runtime behavior and explaining the root cause to users. Information Systems, 90, 101438.
[8] Assaf, R., Giurgiu, I., Pfefferle, J., Monney, S., Pozidis, H., & Schumann, A. (2021). An anomaly detection and explainability framework using convolutional autoencoders for data storage systems. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI) (pp. 5228–5230).
[9] Amarasinghe, K., Kenney, K., & Manic, M. (2018). Toward explainable deep neural network based anomaly detection. In Proceedings of the 11th International Conference on Human System Interaction (HSI) (pp. 311–317).
[10] Du, M., Li, F., Zheng, G., & Srikumar, V. (2017). DeepLog: Anomaly detection and diagnosis from system logs through deep learning. In Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS) (pp. 1285–1298).
[11] Kauffmann, J., Müller, K.-R., & Montavon, G. (2020). Towards explaining anomalies: A deep Taylor decomposition of one-class models. Pattern Recognition, 101, 107198.
[12] Li, Z., Zhao, Y., Han, J., Su, Y., Jiao, R., Wen, X., & Pei, D. (2021). Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3220–3230).
[13] Lipton, Z. C. (2018). The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery. ACM Queue, 16(3), 31–57.
[14] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (pp. 4768–4777).
[15] Hwang, C. H., & Lee, T. (2021). E-SFD: Explainable sensor fault detection in the ICS anomaly detection system. IEEE Access, 9, 140470–140486.
