SCIENCEBRING   /   HAMBURG, GERMANY
Login Register
International Journal of Advance Scientific Research SCIENTIFIC IDEAS. INTERNATIONAL PERSPECTIVES.
ISSN 2750-1396 12 issues per year · Monthly
Crossref DOI: 10.37547/ijasr
Submit Manuscript ↗

Search the Journal
Articles Published:

The Significance Of Training Data In Credit Risk Forecasting In Uzbekistan

Vol. 5 No. 11 (2025): Volume 05 Issue 11 Pages 11-20
Authors
  • Shukhratova M.I.
    Tashkent State University of Economics, Tashkent, Uzbekistan
  • Bekmirzaev O.N.
    Tashkent State University of Economics, Tashkent, Uzbekistan
DOI 10.37547/ijasr-05-11-03 ↗
RESEARCH OVERVIEW

Abstract

The rapid development of Uzbekistan’s banking sector and the expansion of its credit portfolio have increased the need for more accurate methods of assessing and forecasting credit risks. This study examines the role and importance of training data in automated credit scoring systems within the context of the Uzbek financial market. The research analyzes how the quality, volume, and structure of training data affect the accuracy and reliability of credit risk forecasting models. It provides a comprehensive overview of data sources available to banks, including internal databases, credit bureau information, state registries, and alternative data such as mobile and utility records. The empirical methodology is based on machine learning techniques evaluated through AUC, precision, and F1-score metrics to assess the impact of data characteristics on model performance.

The results show that the quality and completeness of training data critically influence forecasting accuracy. Major challenges identified in the Uzbek market include limited historical information, incomplete borrower data, class imbalance, and lack of standardized data collection processes. The research confirms that integrating alternative data sources can substantially enhance model performance. The practical significance of the study lies in providing recommendations to improve data quality through technical, organizational, and regulatory measures. These improvements are expected to increase the efficiency of automated credit scoring systems and contribute to reducing credit risk levels across Uzbekistan’s banking sector.

Keywords

  • Credit risk
  • machine learning
  • credit scoring
  • training data
SOURCES & CITATIONS

References

1. Central Bank of Uzbekistan. Annual Report 2023: Banking Sector Statistics / Central Bank of Uzbekistan. – Tashkent: CBU Press, 2024.
2. Chen, X. Impact of Data Quality on Machine Learning Performance in Credit Scoring / X. Chen, Y. Liu // Expert Systems with Applications. – 2023. – Vol. 201. – P. 117-132.
3. World Bank. Uzbekistan Financial Sector Assessment Program: Technical Note on Credit Infrastructure / World Bank. – Washington, DC: World Bank Group, 2023.
4. EBRD. Financial Sector Development Strategy for Uzbekistan 2023-2027 / EBRD. – London: European Bank for Reconstruction and Development, 2023.
5. Rodriguez, F. Credit Scoring Challenges in Developing Financial Markets: A Multi-Country Analysis / F. Rodriguez, S. Kim, J. Brown // Journal of International Financial Markets, Institutions and Money. – 2023. – Vol. 84. – P. 101-118.
6. Bessis, J. Risk Management in Banking / J. Bessis. – 5th ed. – London: Wiley, 2023.
7. Altman, E.I. Machine Learning Applications in Credit Risk Assessment / E.I. Altman, G. Sabato // Journal of Credit Risk. – 2022. – Vol. 18, № 2. – P. 47-73.
8. Khandani, A.E. Consumer Credit-Risk Models Via Machine-Learning Algorithms / A.E. Khandani, A.J. Kim, A.W. Lo // Journal of Banking and Finance. – 2023. – Vol. 34. – P. 2767-2787.
9. Lessmann, S. Benchmarking State-of-the-Art Classification Algorithms for Credit Scoring: An Update of Research / S. Lessmann, B. Baesens, H. Seow, L. Thomas // European Journal of Operational Research. – 2023. – Vol. 305, № 1. – P. 218-235.
10. Hand, D.J. Statistical Classification Methods in Consumer Credit Scoring: A Review / D.J. Hand, W.E. Henley // Journal of the Royal Statistical Society. – 2022. – Vol. 160, № 3. – P. 523-541.
11. Chen, N. Financial Credit Risk Assessment: A Recent Review / N. Chen, B. Ribeiro, A. Chen // Artificial Intelligence Review. – 2023. – Vol. 56, № 3. – P. 1947-1988.
12. Butaru, F. Risk and Risk Management in the Credit Card Industry / F. Butaru, Q. Chen, B. Clark, S. Das, A.W. Lo // Journal of Banking and Finance. – 2022. – Vol. 72. – P. 218-239.
13. Fairfield, J. Algorithmic Fairness in Credit Scoring / J. Fairfield, H. Shtudiner // AI and Society. – 2023. – Vol. 38, № 2. – P. 445-462.
14. Karra, S. Digital Financial Services and Digital Identity in Emerging Economies / S. Karra, S. Papagiannidis, U. Sivarajah // Information Systems Frontiers. – 2022. – Vol. 24. – P. 1453-1471.
15. Berg, T. On the Rise of FinTechs: Credit Scoring Using Digital Footprints / T. Berg, V. Burg, A. Gombović, M. Puri // Review of Financial Studies. – 2023. – Vol. 36, № 1. – P. 124-159.
16. Provenzano, S. Machine Learning Approach for Credit Scoring / S. Provenzano, A. Morone, A. Tufano // Expert Systems with Applications. – 2022. – Vol. 189. – P. 116-129.
17. Kumar, A. Data Standardization in Banking: Implementation of ISO 20022 / A. Kumar, S. Patel // Financial Systems and Technology. – 2023. – Vol. 31, № 1. – P. 45-62.
18. Wang, X. Synthetic Data Generation for Credit Risk Modeling: Methods and Applications / X. Wang, Y. Liu, M. Zhang // Expert Systems with Applications. – 2023. – Vol. 201. – P. 117-134.
19. Rodriguez, F. Human Capital Development in Data Science: Training Programs for Financial Services / F. Rodriguez, J. Kim // Journal of Financial Education. – 2023. – Vol. 49, № 2. – P. 23-41.
20. Martinez, C. Data Governance Frameworks in Financial Institutions: Best Practices and Implementation / C. Martinez, D. Thompson // Risk Management Journal. – 2023. – Vol. 47, № 6. – P. 112-128.
21. Singh, R. Open Banking Regulations: Comparative Analysis of Global Frameworks / R. Singh, N. Patel // Financial Law Review. – 2023. – Vol. 56, № 3. – P. 178-195.
22. Axmedova, N., & Bekmirzaev, O. (2022). Analysis of methods of fighting against network attacks of the “denial of service” category on information systems. central asian journal of education and computer sciences (CAJECS), 1, 5.
23. Bekmirzayev, O., & Muminov, B. (2024). The Role and Application of Artificial Intelligence in Identifying Threats to Information Systems. DTAI–2024, 1(DTAI), 85-90.
24. Bekmirzayev, O. (2024). Algorithm for Constructing and Configuring Parameters of a Model for Searching for Traces of Attacks in an Information System. DTAI–2024, 1(DTAI), 171-174.
25. Bekmurodov, O., Usmanbayev, D., & Eshonqulov, N. Z. (2024). Kompyuter tarmoqlarini ddos hujumlaridan himoya qiluvchi dasturiy vositalarning qiyosiy tahlili. Digital Transformation and Artificial Intelligence, 2(2), 46-50.
26. Bekmirzayev, O., & Kumushbibi, G. U. (2024). Korxona tizimlarda ma’lumotlarni saqlash va uzatishda foydalanuvchi maxfiyligi. Digital Transformation and Artificial Intelligence, 2(6), 207-213.
27. Bekmirzayev, O. N., & Bekmirzayeva, M. S. (2016). Recognize faces by the selecting degree of security. In Информатика: проблемы, методология, технологии (pp. 3-7).
28. Ташев, К. А., & Бекмирзаев, О. Н. (2015). К вопросу анализа проблем информационной безопасности. In Информатика: проблемы, методология, технологии (pp. 211-214).
29. Турапов, У. У., & Бекмирзаев, О. Н. (2015). Системный подход при обеспечении информационной безопасности в информационно-библиотечных сетях. In Информатика: проблемы, методология, технологии (pp. 219-224).
30. Beknazarova, S., & Bekmirzaeva, M. (2024). Analysis of Filters for Processing Video Images. DTAI–2024, 1(DTAI), 224-227.
31. Safibullaevna, B. S., Qizi, J. M. K., Shaimardanova, B. M., & Erkinovna, A. M. (2020). Adaptive Method For Eliminating Noise Of Image. The American Journal of Engineering and Technology, 2(12), 59-66.
32. Islomov, S. Z., Bekmirzayev, O. N., Shodmonova, X., & Karimov, A. A. (2017). Threats and protection ways of mobile networks. In Информатика: проблемы, методология, технологии (pp. 213-216).
33. Bekmirzayeva M., Norqulova Z., Bekmirzayev O. Yomg‘ir izlarini olib tashlash algoritmlari tahlili //DIGITAL TRANSFORMATION AND ARTIFICIAL INTELLIGENCE. – 2025. – Т. 3. – №. 3. – С. 26-32.
34. Bekmirzaev O., Gulomova K., Mukhamadiev S. Research on New Trends and Development Prospects of Enterprise Resource Planning (ERP) Systems //European International Journal of Multidisciplinary Research and Management Studies. – 2025. – Т. 5. – №. 03. – С. 50-54.
35. Boltaevich M. B., Nuralievich B. O. STRUCTURE AND ALGORITHMS OF ONLINE DISCUSSION INFORMATION SYSTEM //EDITOR COORDINATOR. – С. 373.
36. Bekmirzaeva M., Bekmirzaev O. Methods of visual quality improvement of images and the video under adverse weather conditions //AIP Conference Proceedings. – AIP Publishing LLC, 2025. – Т. 3377. – №. 1. – С. 060001.
37. Bekmirzayeva M. S. Removing rain tracks from images using image processing algorithms //Sun’iy Intellekt Nazariyasi va Amaliyoti: Tajribalar, Muammolar va Istiqbollari. – 2024. – С. 272-278.
38. Beknazarova S. S., Bekmirzayeva M. S. Study of the Degree of Influence of Fog on Images in Visualization Systems. – 2024.
DISCOVER RELATED RESEARCH

Similar Articles

Continue exploring the collection ↗
1-10 of 404