Methodological aspects of the development of credit risk scoring models in the banking sector

Introduction. The modern banking sector operates in a highly competitive environment, with increasing lending volumes and risk management requirements. In this context, assessing borrowers' creditworthiness and minimizing the risk of loan default become crucial. The development of digital technologies and the increasing volume of data necessitates the improvement of analytical tools used in credit scoring. The traditional logistic regression model, with its high level of interpretability, competes with the "black boxes" of machine learning, which offer higher prediction accuracy. This creates an urgent scientific challenge of choosing the optimal methodology for assessing credit risk.

Purpose. The purpose of the study is to analyze the theoretical and methodological foundations of building scoring models based on logistic regression, as well as to identify the factors that affect the quality of credit risk assessment and the effectiveness of using these models in the banking sector.

Materials and methods. The study is based on the works of authors in the field of credit scoring, risk management, and machine learning. The study uses methods of comparative analysis, generalization, and systematization of scientific approaches to building scoring models. Logistic regression is considered as the main analysis tool for predicting the probability of loan default. Modern approaches based on machine learning algorithms are also taken into account.

Results. The study identified key stages in the development of scoring models, including data preparation, feature selection, and parameter estimation. It was found that logistic regression retains significant practical value due to its interpretability and compliance with regulatory requirements. The study also identified key limitations of logistic models, such as their sensitivity to data quality and limited ability to account for complex nonlinear relationships.

Conclusions. Scoring models are a key tool for managing credit risk in banking. Despite the development of more complex algorithms, logistic regression remains popular due to its transparency and reliable results. Improving the efficiency of scoring models requires a comprehensive approach to data quality, proper feature selection, and model adaptation to changing environmental conditions. The core of logistic regression is the maximum likelihood method. In econometrics, the maximum likelihood function is maximized, while in machine learning, the inverse loss function is minimized. A promising area is the combined use of logistic regression with more accurate methods.

1. Komissarov A.R. Analysis of the effectiveness of machine learning methods in predicting credit risk. Naukosfera. 2024;(6-2):312–316. (In Russ.). https://doi.org/10.5281/zenodo.12621417. EDN: EHJLKI

2. Silenko A.N., Tuigunov A.I., Teslyuk V.S. Comparison of the effectiveness of traditional and neural network approaches in banking practice. Journal of Monetary Economics and Management. 2025;(9):412– 419. (In Russ.). https://doi.org/10.26118/2782-4586.2025.75.72.029. EDN: KOOXXR

3. Gibadullina A.A. Bank scoring based on modern digital technologies. In: Digital economy through the eyes of students. Materials of the International Scientific Conference. Kazan; 2023. P. 59–61. (In Russ.). EDN: THIXOL

4. Vanina M.F., Erokhin A.G. Application of machine learning methods in banking scoring. DSPA: issues of digital signal processing application. 2025;15(1):17–35. (In Russ.). EDN: PCWMBW

5. Holda E.D., Idrisov S.A. On the assessment of credit risks in the modern banking system of the Russian Federation. Journal of Economic Studies. 2025;11(2):49–60. (In Russ.). EDN: QBBODG

6. Kantaev N.K. Prospects of using machine learning methods to assess credit risks. The Eurasian Scientific Journal. 2025;17(S2). (In Russ.). EDN: KOGIEQ

7. Dyakonova L.P., Konstantinov A.F., Kitova O. ., Kitov V.A. Application of machine learning and artificial intelligence methods in the field of lending and fraud detection. UGOL' (Russian Coal Journal). 2025;10(1198):63–69. (In Russ.). https://doi.org/10.18796/0041-5790-2025-10-63-69. EDN: FLXTEK

8. Dyadyunov D.A. Machine learning for risk management in a bank: opportunities and challenges. Vestnik nauki. 2025;1(1(82)):265–273. (In Russ.). EDN: OJWRUL

9. Kremer N.S. Probability theory and mathematical statistics : textbook and practical course for universities, 5th ed., revised. Moscow: Yurait Publishing House; 2026. 538 p. (In Russ.). ISBN 978-5-534- 10004-4

10. Operations Research in Economics : textbook for universities. N. S. Kremer (ed.). – 4th ed., revised and additional. Moscow: Yurayt Publishing House, 2026. 414 p. (In Russ.). ISBN 978-5-534-12800-0

11. Mikhailova S.S., Grineva N.V., Kontsevaya N.V. Econometrics: Textbook for undergraduate studies. Moscow: Prometey; 2024. 512 p. (In Russ.). ISBN: 978-5-00172-626-5. EDN: RHNTBU

12. Rashka S., Mirjalili V. Python and machine learning. Machine learning and deep learning using Python, scikit-learn and TensorFlow 2. Translated from English and edited by Yu.N. Artemenko. – 3rd ed. Moscow: Dialektika; St. Petersburg: Dialektika; 2020. 848 p. (In Russ.). ISBN 978-5-907203-57-0