Real-Time Graph-Based Anomaly Detection for Capital Markets Using Stream Processing
DOI:
https://doi.org/10.22399/ijcesen.4211Keywords:
Graph-Based Anomaly Detection, Capital Market Surveillance, Stream Processing, Graph Neural Networks (GNNs), Real-Time Financial AnalyticsAbstract
The growing complexity and speed of trading activities in capital markets have rendered rule-based anomaly detection systems incapable of following real-time monitoring. The paper examines the model of integrating graph-based modeling and stream processing architecture on financial transactions as an effective framework to detect anomalous behaviors of financial transactions. Via the representation of the market entities and their relations as dynamic graphs and the application of the machine learning model, leveraging a graph neural network to them, it is possible to detect market anomalies, like fraud, market manipulation, and insider trading, with a more in-depth understanding of the context and a faster pace. Stream processing engines (e.g., Apache Kafka, Flink) facilitate large-scale throughput, low-latency data ingestion, whereas graph forms describe non-linear as well as dynamic relationships between brokers, traders, and instruments. In the paper, architectural, machine-learning, and compliance-based deployment criteria needed to operationalize such systems are discussed. It also covers more complex subjects, such as cross-market graph correlation, federated learning, and explainability in high-stakes settings. Results indicate that graph-based real-time anomaly detection systems bring a dramatic improvement in scalability, accuracy, and compliance, as well as represent the first essential step towards proactive financial market surveillance
References
1. Akoglu, L., Tong, H., & Koutra, D. (2015). Graph-based anomaly detection and description: a survey. Data mining and knowledge discovery, 29, 626-688.
2. Rasul, I., Shaboj, S. I., Rafi, M. A., Miah, M. K., Islam, M. R., & Ahmed, A. (2024). Detecting Financial Fraud in Real-Time Transactions Using Graph Neural Networks and Anomaly Detection. Journal of Economics, Finance and Accounting Studies, 6(1), 131-142.
3. Ye, C., Li, Y., He, B., Li, Z., & Sun, J. (2021, June). Gpu-accelerated graph label propagation for real-time fraud detection. In Proceedings of the 2021 International Conference on Management of Data (pp. 2348-2356).
4. Deng, C., Duan, Y., Jin, X., Chang, H., Tian, Y., Liu, H., ... & Zhuang, J. (2024). Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey. arXiv preprint arXiv:2406.05392.
5. Gudimetla, A. R. REAL-TIME FRAUD DETECTION: INTEGRATING EVENT-DRIVEN ARCHITECTURES WITH GRAPH NEURAL NETWORKS.
6. Pazho, A. D., Noghre, G. A., Purkayastha, A. A., Vempati, J., Martin, O., & Tabkhi, H. (2023). A survey of graph-based deep learning for anomaly detection in distributed systems. IEEE Transactions on Knowledge and Data Engineering, 36(1), 1-20.
7. Morishima, S. (2021). Scalable anomaly detection in blockchain using graphics processing unit. Computers & Electrical Engineering, 92, 107087.
8. Ekle, O. A., & Eberle, W. (2024). Anomaly detection in dynamic graphs: A comprehensive survey. ACM Transactions on Knowledge Discovery from Data, 18(8), 1-44.
9. Trinh, T. K., & Wang, Z. (2024). Dynamic graph neural networks for multi-level financial fraud detection: A temporal-structural approach. Annals of Applied Sciences, 5(1).
10. Odofin, O. T., Abayomi, A. A., Uzoka, A. C., Adekunle, B. I., Agboola, O. A., & Owoade, S. (2024). Designing Event-Driven Architecture for Financial Systems Using Kafka, Camunda BPM, and Process Engines.
11. Liu, Y., Ding, K., Lu, Q., Li, F., Zhang, L. Y., & Pan, S. (2023). Towards self-interpretable graph-level anomaly detection. Advances in Neural Information Processing Systems, 36, 8975-8987.
12. George, J. G. (2023). Advancing Enterprise Architecture for Post-Merger Financial Systems Integration in Capital Markets laying the Foundation for Machine Learning Application. Aus. J. ML Res. & App, 3(2), 429.
13. Goyal, A., Liu, J., Bates, A., & Wang, G. (2024). ORCHID: Streaming Threat Detection over Versioned Provenance Graphs. arXiv preprint arXiv:2408.13347.
14. Hu, W., Yang, F., Mao, X., Chen, R., Fan, K., & Xie, J. (2024, January). Ranking the spreading influence of nodes in weighted networks by combining node2vec and weighted K-Shell decomposition. In 2024 4th International Conference on Neural Networks, Information and Communication (NNICE) (pp. 588-597). IEEE.
15. Liu, J., Zhang, Y., Meng, K., Xu, Y., & Dong, Z. Y. (2022, November). Risk-averse graph learning for real-time power system emergency load shedding. In 2022 IEEE PES Innovative Smart Grid Technologies-Asia (ISGT Asia) (pp. 520-524). IEEE.
16. Liu, F., Jung, J., Feinstein, W., D'Ambrogia, J., & Jung, G. (2024, October). Aggregated Knowledge Model: Enhancing Domain-Specific QA with Fine-Tuned and Retrieval-Augmented Generation Models. In Proceedings of the 4th International Conference on AI-ML Systems (pp. 1-7).
17. da Silva Veith, A., de Assuncao, M. D., & Lefevre, L. (2021). Latency-aware strategies for deploying data stream processing applications on large cloud-edge infrastructure. IEEE transactions on cloud computing.
18. Troupiotis-Kapeliaris, A., Kastrisios, C., & Zissis, D. (2025). Vessel Trajectory Data Mining: a review. IEEE Access.
19. Hassan, H. B., Barakat, S. A., & Sarhan, Q. I. (2021). Survey on serverless computing. Journal of Cloud Computing, 10(1), 39.
20. Bruno, D. R., Berri, R. A., Barbosa, F. M., & Osório, F. S. (2023). CARINA Project: Visual perception systems applied for autonomous vehicles and advanced driver assistance systems (ADAS). IEEE Access, 11, 69720-69749.
21. Fu, D., Bao, W., Maciejewski, R., Tong, H., & He, J. (2023). Privacy-preserving graph machine learning from data to computation: A survey. ACM SIGKDD Explorations Newsletter, 25(1), 54-72.
22. Khanzadeh, S., Neto, E. C. P., Iqbal, S., Alalfi, M., & Buffett, S. (2025). An exploratory study on domain knowledge infusion in deep learning for automated threat defense. International Journal of Information Security, 24(1), 1-19.
23. Wang, H., Lu, Y., Shutters, S. T., Steptoe, M., Wang, F., Landis, S., & Maciejewski, R. (2018). A visual analytics framework for spatiotemporal trade network analysis. IEEE transactions on visualization and computer graphics, 25(1), 331-341.
24. Zakrzewicz, M., Wojciechowski, M., & Gławiński, P. (2019). Solution pattern for anomaly detection in financial data streams. In New Trends in Databases and Information Systems: ADBIS 2019 Short Papers, Workshops BBIGAP, QAUCA, SemBDM, SIMPDA, M2P, MADEISD, and Doctoral Consortium, Bled, Slovenia, September 8–11, 2019, Proceedings 23 (pp. 77-84). Springer International Publishing.
25. Saadati, P., Abdelnour-Nocera, J., & Clemmensen, T. (2020). Proposed system for a socio-technical design framework for improved user collaborations with automation technologies. In Human Computer Interaction and Emerging Technologies. Cardiff University Press.
26. Reynisson, K., Schreyer, M., & Borth, D. (2024). GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs. arXiv preprint arXiv:2407.12440.
27. Krichen, M. (2023). Convolutional neural networks: A survey. Computers, 12(8), 151.
28. Zhong, H., Yang, D., Shi, S., Wei, L., & Wang, Y. (2024). From data to insights: the application and challenges of knowledge graphs in intelligent audit. Journal of Cloud Computing, 13(1), 114.
29. Venugopal, K., & Jagadeesh, B. (2024). Theoretical Insights Into User Security and Privacy in Social. Human Impact on Security and Privacy: Network and Human Security, Social Media, and Devices: Network and Human Security, Social Media, and Devices, 289.
30. Dou, F., Ye, J., Yuan, G., Lu, Q., Niu, W., Sun, H., ... & Song, W. (2023). Towards artificial general intelligence (AGI) in the internet of things (iot): Opportunities and challenges. arXiv preprint arXiv:2309.07438.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
