COMPARATIVE ANALYSIS OF ENSEMBLE MACHINE LEARNING MODELS FOR CREDIT SCORING AND FRAUD DETECTION IN FINANCIAL DECISION SUPPORT SYSTEMS

This paper investigates the performance of ensemble machine learning algorithms - Random Forest, Gradient Boosting, and XGBoost - for solving the dual-classification problem of credit scoring and fraud detection within financial decision support systems. The study utilizes an event-driven architecture for real-time data processing, evaluated on retail lending application data through cross-validation and hyperparameter optimization. Experimental results demonstrate that Random Forest and XGBoost achieve high predictive accuracy for credit scoring, while boosting models effectively handle fraud detection. Furthermore, cost-sensitive threshold calibration optimizes risk management, and feature importance analysis reveals that behavioral and data consistency indicators outweigh traditional credit scores. The findings offer a robust methodological and architectural contribution to real-time financial decision support systems, enhancing automated risk assessment and fraud mitigation in digital lending.

1. National Bank of the Republic of Kazakhstan. Banking sector statistics for 2024–2025 [Electronic resource]. – URL: https://www.nationalbank.kz (accessed: 20.01.2026).

2. Agency of the Republic of Kazakhstan for the Regulation of the Financial Market. Annual Report 2024–2025 [Electronic resource]. – URL: https://www.afsa.kz (accessed: 20.01.2026).

3. Xie X., Zhang F., Liu L., Yang Y., Hu X. Assessment of associated credit risk in the supply chain based on trade credit risk contagion // PLOS ONE. – 2023. – Vol. 18, No. 2. – https://doi.org/10.1016/j.ejor.2021.05.038.

4. Peng K., Yan G. A survey on deep learning for financial risk prediction // Quantitative Finance and Economics. — 2021. — Vol. 5, No. 4. — P. 716–737. — https://doi.org/10.3934/QFE.2021032.

5. V. Moscato, A. Picariello, and G. Sperli, "A benchmark of machine learning approaches for credit score prediction," Expert Systems with Applications, vol. 165, p. 113986, 2021. https://doi.org/10.1016/j.eswa.2020.113986.

6. S. Lessmann, B. Baesens, H. Seow, and L. C. Thomas, "Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research," European Journal of Operational Research, vol. 247, no. 1, pp. 124–136, 2015. https://doi.org/10.1016/j.ejor.2015.05.030.

7. N. Bussmann, P. Giudici, D. Marinelli, and J. Papenbrock, "Explainable machine learning in credit risk management," Computational Economics, vol. 57, pp. 203–216, 2021. https://doi.org/10.1007/s10614-020-10042-0.

8. Mestiri, S. Credit scoring using machine learning and deep learning-based models // Data Science in Finance and Economics. – 2024. – Vol. 4, No. 2. – P. 236–248. – https://doi.org/10.3934/DSFE.2024009.

9. Alatawi, M. Credit card fraud detection under extreme class imbalance using ensemble machine learning approaches // Applied Sciences. – 2025. – Vol. 15, No. 3. – Art. 6734. – https://doi.org/10.3390/app15036734.

10. Apache Software Foundation. Apache Kafka Documentation [Electronic resource]. – URL: https://kafka.apache.org/documentation (accessed: 01.02.2026).

11. Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45, No. 1. – P. 5–32. – https://doi.org/10.1023/A:1010933404324.

12. Friedman J.H. Greedy function approximation: a gradient boosting machine // Annals of Statistics. – 2001. – Vol. 29, No. 5. – P. 1189–1232. – https://doi.org/10.1214/aos/1013203451.

13. Chen T., Guestrin C. XGBoost: a scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD. – 2016. – P. 785–794. – https://doi.org/10.1145/2939672.2939785.

14. LoanGuard DSS: Architecture and Implementation of a Real-Time Credit Scoring and Fraud Detection System / D. Mityanin, D. Akhmadiyev, T. Berdamurat – Report, the International Campus, M. Kozybaev NKU. – Petropavlovsk, 2026. – 45 p.

15. Pedregosa F. et al. Scikit-learn: machine learning in Python // Journal of Machine Learning Research. – 2011. – Vol. 12. – P. 2825–2830. – https://doi.org/10.5555/1953048.2078195.

16. Artillery.io. Artillery Load Testing Documentation [Electronic resource]. – URL: https://www.artillery.io/docs (accessed: 10.03.2026).

17. Dal Pozzolo A., Caelen O., Johnson R.A., Bontempi G. Calibrated Probability with Undersampling for Unbalanced Credit Card Fraud Detection // IEEE Transactions on Neural Networks and Learning Systems. – 2018. – Vol. 29, No. 10. – P. 4649–4662. – https://doi.org/10.1109/SSCI.2015.33.

18. Ala’raj M., Majdalawieh M., Abbod M.F. An explainable data-driven decision support framework for strategic customer development // Knowledge-Based Systems. – 2024. – Vol. 295. – Art. 111761. – https://doi.org/10.1016/j.knosys.2024.111761.

19. Hadji Misheva B., Osterrieder J., Hirsa A., Kulkarni O., Lin S. F. Explainable AI in Credit Risk Management // arXiv:2103.00949. — 2021. — https://doi.org/10.48550/arXiv.2103.00949.