A Hybrid Modular Architecture for Fraud Detection Using Offline and Online Machine Learning Models
Caprian Iurie

Caprian, Iurie. (2025) “A Hybrid Modular Architecture for Fraud Detection Using Offline and Online Machine Learning Models.” The Problems of Economy 3:312–320.
https://doi.org/10.32983/2222-0712-2025-3-312-320

Section: Mathematical methods and models in economy

UDC 004.8:005.8

Abstract:
This article proposes a hybrid and modular architecture for fraud detection that integrates both offline and online machine learning models to address challenges in dynamic financial transaction environments. The framework combines high-performance offline models, including XGBoost, LightGBM, and deep neural networks, with lightweight and adaptive online learners, such as Hoeffding Trees and Adaptive Random Forests, enabling accurate detection in both historical datasets and real-time streaming transactions. A key methodological contribution lies in balancing predictive performance, responsiveness, and interpretability, achieved through a weighted risk scoring mechanism and a unified cost-sensitive evaluation framework that aligns technical metrics with tangible financial impacts. The architecture emphasizes modularity and scalability, facilitating continuous adaptation via concept drift detection and feedback-driven retraining. Its implementation in a containerized, open-source environment ensures reproducibility, robustness, and seamless deployment in production-grade financial ecosystems, even under high-volume transactional loads. The proposed system effectively bridges the gap between advanced machine learning research and operational requirements, providing a flexible, interpretable, and operationally viable solution for modern fraud detection.Furthermore, this study consolidates previous work by the author on intelligent fraud detection systems, extending prior contributions in model selection, AI interpretability, and economic evaluation of false positives in banking contexts. Future research directions include integrating graph-based relational features for network fraud detection, applying reinforcement learning for adaptive decision optimization, and employing federated learning techniques to enhance data privacy across institutions. Overall, the proposed framework represents a scalable, transparent, and adaptive approach that evolves alongside emerging fraud strategies, delivering a deployable system with practical and financial relevance.

Keywords: fraud detection, hybrid architecture, machine learning, concept drift, model evaluation, explainability, financial risk.

Fig.: 6. Formulae: 5. Bibl.: 12.

Caprian Iurie – Postgraduate Student, State University of Moldova (60 Alexei Mateevici Str., Chisinau, Moldova)
Email: iuriecaprian@gmail.com

List of references in article

Bahnsen, A. C., Aouada, D., Ottersten, B. (2016). Example-dependent cost-sensitive decision trees. Expert Systems with Applications, 42(19), 6609–6619. https://doi.org/10.1016/j.eswa.2015.04.070
Bifet, A., Holmes, G., Pfahringer, B., Kirkby, R., & Gavald?, R. (2011). New ensemble methods for evolving data streams. Proceedings of the 15th ACM SIGKDD, 139–148.
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000). LOF: Identifying density-based local outliers. ACM SIGMOD Record, 29(2), 93–104.
Caprian, I. (2023). The Application of Artificial Intelligence for the Purpose of Combating Bank Fraud. The Problems of Economy, 2, 204–212. https://doi.org/10.32983/2222-0712-2023-2-204-212
Caprian, I. (2023). The Use of Machine Learning for the Purpose of Combating Bank Fraud. Business Inform., 7, 140–145. https://doi.org/10.32983/2222-4459-2023-7-140-145
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794. https://doi.org/10.1145/2939672.2939785
Gama, J., Zliobaite, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM Computing Surveys (CSUR), 46, 44.
Khammas, B., & Roushangar, K. (2020). A hybrid offline–online architecture for adaptive fraud detection in online payments. Expert Systems with Applications, 159, 113620. https://doi.org/10.1016/j.eswa.2020.113620
Liu, Y., Li, J., Yang, Y., Yu, L., & Zhang, C. (2019). A cost-sensitive ensemble method for fraud detection based on dynamic updating. Information Sciences, 476, 421–439.
Montiel, J., Read, J., Bifet, A., & Abdessalem, T. (2021). River: machine learning for streaming data in Python. Journal of Machine Learning Research, 22(1), 1–9.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why Should I Trust You?": Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD, 1135–1144.
Zliobaite, I. (2010). Learning under concept drift: an overview. arXiv preprint arXiv:1010.4784.