koz"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"Bulletin of Manash Kozybayev North Kazakhstan University2958-003X2958-0048М. Қозыбаев атындағы СҚУ10.54596/2958-0048-2026-3-309-318koz-2836Research ArticleИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИINFORMATION AND COMMUNICATION TECHNOLOGIESСРАВНИТЕЛЬНЫЙ АНАЛИЗ АНСАМБЛЕВЫХ МОДЕЛЕЙ МАШИННОГО ОБУЧЕНИЯ ДЛЯ КРЕДИТНОГО СКОРИНГА И ОБНАРУЖЕНИЯ МОШЕННИЧЕСТВА В СИСТЕМАХ ПОДДЕРЖКИ ФИНАНСОВЫХ РЕШЕНИЙCOMPARATIVE ANALYSIS OF ENSEMBLE MACHINE LEARNING MODELS FOR CREDIT SCORING AND FRAUD DETECTION IN FINANCIAL DECISION SUPPORT SYSTEMSМитянинД. М.MityaninD.

Петропавловск

student

Petropavlovsk

is2077@ku.edu.kzАхмадиевД. Р.AkhmadiyevD.

Петропавловск

student

Petropavlovsk

is2265@ku.edu.kzБердамуратТ. С.BerdamuratT.

Петропавловск

Petropavlovsk

is2067@ku.edu.kzhttps://orcid.org/0000-0001-8402-8323КимГ. А.KimG.

Петропавловск

corresponding author, PhD

Petropavlovsk

gakim@ku.edu.kzhttps://orcid.org/0000-0002-8580-7326СеменюкВ. В.SemenyukV.

Петропавловск

Master

Petropavlovsk

vvsemenyuk@ku.edu.kzhttps://orcid.org/0009-0008-3100-8036LucenaJoe Robert Paul G.LucenaJoe Robert Paul G.

Макати

Program Director of Civil Engineering

Makati City

joerobertpaull@apc.edu.phНАО «Северо-Казахстанский университет имени Манаша Козыбаева»КазахстанManash Kozybayev North Kazakhstan University NPLCKazakhstanАзиатско-Тихоокеанский колледжФилиппиныAsia Pacific CollegePhilippines20263009202603 (71)309318Copyright © Митянин Д.М., Ахмадиев Д.Р., Бердамурат Т.С., Ким Г.А., Семенюк В.В., Lucena J., 20262026Митянин Д.М., Ахмадиев Д.Р., Бердамурат Т.С., Ким Г.А., Семенюк В.В., Lucena J.Mityanin D., Akhmadiyev D., Berdamurat T., Kim G., Semenyuk V., Lucena J.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.ku.edu.kz/jour/article/view/2836

В данной статье исследуется эффективность ансамблевых алгоритмов машинного обучения (Random Forest, Gradient Boosting, XGBoost) для решения задачи кредитного скоринга и обнаружения мошенничества в системах поддержки принятия финансовых решений. Исследование базируется на событийно-ориентированной архитектуре для обработки данных в реальном времени, методах перекрестной валидации и оптимизации гиперпараметров на данных розничного кредитования. Экспериментальные результаты показывают, что Random Forest и XGBoost достигают высокой точности в кредитном скоринге, а алгоритмы бустинга эффективны для выявления мошенничества. Калибровка классификационного порога оптимизирует управление рисками, а анализ важности признаков подтверждает, что поведенческие показатели превосходят традиционные кредитные рейтинги по предиктивной силе. Полученные результаты вносят значимый научный и практический вклад в развитие систем поддержки финансовых решений, обеспечивая автоматизацию оценки рисков и защиту от мошенничества в цифровом кредитовании.

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.

кредитный скорингобнаружение мошенничестваRandom ForestGradient BoostingXGBoostансамблевые методысистема поддержки принятия решенийApache Kafkaмашинное обучениеcredit scoringfraud detectionRandom ForestGradient BoostingXGBoostensemble methodsdecision support systemApache Kafkamachine learningReferencesNational Bank of the Republic of Kazakhstan. Banking sector statistics for 2024–2025 [Electronic resource]. – URL: https://www.nationalbank.kz (accessed: 20.01.2026).National Bank of the Republic of Kazakhstan. Banking sector statistics for 2024–2025 [Electronic resource]. – URL: https://www.nationalbank.kz (accessed: 20.01.2026).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).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).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.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.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.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.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.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.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.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.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.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.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.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.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.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.Apache Software Foundation. Apache Kafka Documentation [Electronic resource]. – URL: https://kafka.apache.org/documentation (accessed: 01.02.2026).Apache Software Foundation. Apache Kafka Documentation [Electronic resource]. – URL: https://kafka.apache.org/documentation (accessed: 01.02.2026).Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45, No. 1. – P. 5–32. – https://doi.org/10.1023/A:1010933404324.Breiman L. Random forests // Machine Learning. – 2001. – Vol. 45, No. 1. – P. 5–32. – https://doi.org/10.1023/A:1010933404324.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.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.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.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.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.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.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.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.Artillery.io. Artillery Load Testing Documentation [Electronic resource]. – URL: https://www.artillery.io/docs (accessed: 10.03.2026).Artillery.io. Artillery Load Testing Documentation [Electronic resource]. – URL: https://www.artillery.io/docs (accessed: 10.03.2026).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.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.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.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.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.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.

The authors declare that there are no conflicts of interest present.