kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2025-22-3-98-109kaz29-2107Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEСКОРИНГОВЫЕ КАРТЫ ДЛЯ РАЗЛИЧНЫХ ТИПОВ КРЕДИТНЫХ ПРОДУКТОВSCORING CARDS FOR DIFFERENT TYPES OF CREDIT PRODUCTShttps://orcid.org/0009-0009-8273-3147ОрдабаеваЖ.OrdabaevaZh.

докторант

г. Алматы

PhD student

Almaty

zhannaordabayeva@gmail.comhttps://orcid.org/0000-0003-0568-3114Hallaçİbrahim RızaHallaçİbrahim Rıza

ассоциированный профессор

г. Алматы

Associate Professor

Almaty

ibrahim.hallac@alanya.edu.trhttps://orcid.org/0000-0002-1596-561XМолдагуловаА. Н.MoldagulovaA. N.

к.ф.-м.н., ассоциированный профессор

г. Алматы

 Cand.Phys-Math.Sc., Associate Professor 

 Almaty 

aiman.moldagulova@gmail.comКазахский национальный исследовательский технический университет им. К.И. СатпаеваКазахстанKazakh National Research Technical University named after K.I. SatbayevKazakhstan20252709202522398109Copyright © Ордабаева Ж., Hallaç İ., Молдагулова А.Н., 20252025Ордабаева Ж., Hallaç İ., Молдагулова А.Н.Ordabaeva Z., Hallaç İ., Moldagulova A.N.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/2107

Развитие кредитного скоринга является одной из ключевых тем, на которые обращают внимание при управлении кредитными рисками в финансовых компаниях. Однако единый подход к созданию рейтинговых карт зачастую бесполезен, поскольку кредитные продукты различаются по уровню риска и срокам финансирования, а информации о заемщиках зачастую недостаточно. В статье рассматриваются особенности создания кредитных карт для потребительского кредитования, рефинансирования, малого и среднего бизнеса, автокредитования, ипотечного кредитования, финтеха и P2P-кредитования. Таким образом, настоящую работу можно рассматривать как приведенный выше сравнительный анализ наиболее важных элементов, влияющих на вероятность дефолта заемщика при расчетах по сегментам, вместе с рассмотрением методов машинного обучения и использованием альтернативных источников данных, которые могут повысить точность прогноза. В зависимости от обычного кредитного продукта анализ позволяет выработать рекомендации по выбору оптимального подхода к созданию скоринговых карт, что повышает точность прогнозирования кредитоспособности заемщика и снижает степень риска дефолта.

The development of credit scoring is one of the key topics of attention in credit risk management in financial companies. However, a single approach to produce rating cards is frequently worthless since loan products differ in risk and financing time and often there is insufficient information on borrowers. The paper addresses the features of creating score cards for consumer credit, refinancing, small and medium businesses, auto loans, mortgage loans, fintech and P2P lending. Thus, the present work can be considered as the above comparative analysis of the most important elements influencing the probability of default of the borrower in the settlement by segments, together with the consideration of machine learning techniques and the use of alternative data sources that can improve the accuracy of the forecast. Depending on the usual credit product, the analysis lets one create recommendations for choosing the optimal approach of creating scoring cards, so enhancing the accuracy of the borrower’s creditworthiness projection and reducing the degree of default risk.

кредитный скорингскоринговые картыкредитные продуктырефинансированиемашинное обучениеуправление рискамикредитоспособностьальтернативные данныеcredit scoringscoring cardscredit productsrefinancingmachine learningrisk managementcreditworthinessalternative dataReferencesAddo P.M., Guegan D., Hassani B. Credit risk analysis using machine and deep learning models // Risks. – 2018. – V. 6. – No. 2. – P. 38. – https://doi.org/10.3390/risks6020038.Addo, P.M., Guegan, D., & Hassani, B. Credit risk analysis using machine and deep learning models. Risks, 6 (2), 38 (2018). https://doi.org/10.3390/risks6020038.Brown I., Mues C. An experimental comparison of classification algorithms for imbalanced credit scoring datasets // Expert Systems with Applications. – 2012. – V. 39. – No. 3. – P. 3446–3453. – https://doi.org/10.1016/j.eswa.2011.09.033.Brown, I., & Mues, C. An experimental comparison of classification algorithms for imbalanced credit scoring datasets. Expert Systems with Applications, 39 (3), 3446–3453 (2012). https://doi.org/10.1016/j.eswa.2011.09.033.Grier D.A. Credit Scoring and Credit Control. – Oxford: Oxford University Press, 2012.Grier, D.A. Credit Scoring and Credit Control. Oxford University Press (2012).Henley W.E., Hand D.J. A k-nearest-neighbour classifier for assessing consumer credit risk // The Statistician. – 1996. – V. 45. – No. 1. – P. 77–95. – https://doi.org/10.2307/2988486.Henley, W.E., & Hand, D.J. A k-nearest-neighbour classifier for assessing consumer credit risk. The Statistician, 45 (1), 77–95 (1996). https://doi.org/10.2307/2988486.Munkhdalai L., Namsrai O.B., Lee J.Y., Ryu K.H. An empirical comparison of machine-learning methods on bank client credit assessments // Sustainability. – 2019. – V. 11. – No. 3. – P. 699. – https://doi.org/10.3390/su11030699.Munkhdalai, L., Namsrai, O.B., Lee, J.Y., & Ryu, K.H. An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability, 11 (3), 699 (2019). https://doi.org/10.3390/su11030699.Oguz K., Ugur O., Kestel A. S. The impact of feature selection and transformation on machine learning methods in determining credit scoring // arXiv preprint. – 2023. – arXiv:2303.05427. – URL: https://arxiv.org/abs/2303.05427.Oguz, K., Ugur, O., & Kestel, A.S. The impact of feature selection and transformation on machine learning methods in determining credit scoring. (2023). arXiv preprint, arXiv:2303.05427. Retrieved from https://arxiv.org/abs/2303.05427.Tatarintsev M.A., Nikitin P.V., Gorokhova R.I., Dolgov V.I. Comparative analysis of machine learning technologies for credit scoring tasks // Fundamental Research. – 2022. – V. 2. – P. 7–12. – https://doi.org/10.17513/fr.43419.Tatarintsev, M.A., Nikitin, P.V., Gorokhova, R.I., & Dolgov, V.I. Comparative analysis of machine learning technologies for credit scoring tasks. Fundamental Research, 2, 7–12 (2022). https://doi.org/10.17513/fr.43419.XGBoost Documentation. Random Forests™ in XGBoost. – URL: https://xgboost.readthedocs.io/en/stable/tutorials/rf.html (дата обращения: 13.02.2025).XGBoost Documentation. (n.d.). Random Forests™ in XGBoost. Retrieved from https://xgboost.readthedocs.io/en/stable/tutorials/rf.html.Kadiev A.D., Chibisova A.V. Neural network methods for credit scoring // Mathematical Modeling and Numerical Methods. – 2022. – V. 4. – P. 81–92. – URL: https://mmcm.bmstu.ru/articles/download_article/295/.Kadiev, A.D., & Chibisova, A.V. Neural network methods for credit scoring. Mathematical Modeling and Numerical Methods, 4, 81–92 (2022). URL: https://mmcm.bmstu.ru/articles/download_article/295/.Hu L., Chen D., Wong J., Yang H., Wang K., Sudjianto A., Nair V. N. Supervised machine learning techniques: An overview with applications to banking // arXiv preprint. – 2020. – arXiv:2008.04059. – URL: https://arxiv.org/abs/2008.04059.Hu, L., Chen, D., Wong, J., Yang, H., Wang, K., Sudjianto, A., & Nair, V. N. (2020). Supervised machine learning techniques: An overview with applications to banking. arXiv preprint, arXiv:2008.04059. URL: https://arxiv.org/abs/2008.04059.Shukhardin A. V. Development of a credit scoring system based on machine learning models // Ural Federal University Electronic Archive. – 2024. – URL: https://elar.urfu.ru/bitstream/10995/140553/1/m_th_a.v.shukhardin_2024.pdf.Shukhardin, A.V. (2024). Development of a credit scoring system based on machine learning models. Ural Federal University Electronic Archive. URL: https://elar.urfu.ru/bitstream/10995/140553/1/m_th_a.v.shukhardin_2024.pdf.Arram A., Ayob M., AlBadr M. A. A., Suleiman A., Albashish D. Credit rating prediction using machine learning models: A new dataset // arXiv preprint. – 2023. – arXiv:2310.02956. – URL: https://arxiv.org/abs/2310.02956.Arram, A., Ayob, M., AlBadr, M. A.A., Suleiman, A., & Albashish, D. Credit rating prediction using machine learning models: A new dataset. (2023). arXiv preprint, arXiv:2310.02956. URL: https://arxiv.org/abs/2310.02956.Rastorguev A.V., Mikishanina E.V. Building a scoring model for assessing borrower creditworthiness // Электронный научный журнал «Вектор экономики». – 2022. – No. 5. – URL: https://www.vectoreconomy.ru/images/publications/2022/5/mathematicalmethods/Rastorguev_Mikishanina.pdf.Rastorguev, A.V., & Mikishanina, E.V. Building a scoring model for assessing borrower creditworthiness. Electronic Scientific Journal “Vector of Economics, 5”. (2022). URL: https://www.vectoreconomy.ru/images/publications/2022/5/mathematicalmethods/Rastorguev_Mikishanina.pdf.Dauletkhanuly Y., Oyshynova G. A. The use of machine learning and artificial intelligence by the monetary regulator // Economic Review of the National Bank of the Republic of Kazakhstan. – 2023. – No. 4. – URL: https://nationalbank.kz/file/download/98995.Dauletkhanuly, Y., & Oyshynova, G. A. The use of machine learning and artificial intelligence by the monetary regulator. Economic Review of the National Bank of the Republic of Kazakhstan, 4 (2023). URL: https://nationalbank.kz/file/download/98995.Центральный банк Российской Федерации. The impact of negative news on public perception of inflation // Рабочие материалы Банка России. – 2022. – No. 111. – URL: https://www.cbr.ru/content/document/file/144918/wp_111.pdf.Central Bank of the Russian Federation. The impact of negative news on public perception of inflation. Working Papers of the Bank of Russia, 111 (2022). URL: https://www.cbr.ru/content/document/file/144918/wp_111.pdf. [in Russian].Biecek P., Chlebus M., Gajda J., Gosiewska A., Kozak A., Ogonowski D., Sztachelski J., Wojewnik P. Enabling machine learning algorithms for credit scoring: Explainable artificial intelligence (XAI) methods for clear understanding complex predictive models // arXiv preprint. – 2023. – arXiv:2310.02956. – URL: https://arxiv.org/abs/2310.02956.Biecek, P., Chlebus, M., Gajda, J., Gosiewska, A., Kozak, A., Ogonowski, D., Sztachelski, J., & Wojewnik, P. (2023). Enabling machine learning algorithms for credit scoring: Explainable artificial intelligence (XAI) methods for clear understanding complex predictive models. arXiv preprint, arXiv:2310.02956. URL: https://arxiv.org/abs/2310.02956.

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