SUN’IY INTELLEKT QO‘LLAB- QUVVATLOVIDAGI KREDIT QARORLARINING MOLIYAVIY SAMARASINI KVAZIEKSPERIMENTAL BAHOLASH: O‘ZMILLIYBANK MISOLIDA
DOI:
https://doi.org/10.5281/zenodo.23258933Abstract
Sun’iy intellekt (SI) qo‘llab-quvvatlaydigan kredit qarorlarining moliyaviy samaradorligini aniqlash uchun kvazieksperimental baholash dizayni taklif etilib, u “O‘zbekiston Respublikasi Tashqi iqtisodiy faoliyat milliy banki” AJ (keyingi o‘rinlarda – O‘zmilliybank, NBU) misolida hisob-kitob asosida sinovdan o‘tkazilgan. Tadqiqotning dolzarbligi tizim uchun ahamiyatli banklarda kredit portfelining jadal o‘sishi (2019–2026-yillarda bank tizimi bo‘yicha 167,4 trln so‘mdan 604,0 trln so‘mgacha, o‘rtacha yillik 20,1 foiz) hamda SI modeli xatolarining ko‘p sonli moliyaviy qarorlarga tezkor tarzda ko‘chib, portfel sifatiga ta’sir ko‘rsatishi ehtimoli bilan belgilanadi. Uch rejimli taqqoslash sxemasi ishlab chiqilgan: an’anaviy (SIsiz) qaror; SI tavsiyasi va mazmunli inson tasdig‘iga asoslangan qaror; yuqori darajada avtomatlashtirilgan qaror. Rejimlar o‘rtasidagi sababiy farqlarni aniqlash uchun ehtimollik balli bo‘yicha moslashtirish (propensity score matching) va “farqlar farqi” (difference-in-differences) usullari, shuningdek, bank, mahsulot va vaqt bo‘yicha fiksirlangan effektlardan foydalanish taklif etilgan. Moliyaviy samaradorlik kutilayotgan kredit yo‘qotishlari, risk qiymati, sof foiz marjasi va iqtisodiy kapital ko‘rsatkichlari orqali baholanadi. NBUning 2026-yil 1-yanvar holatiga 105,382 trln so‘mlik kredit portfeli asosida amalga oshirilgan hisob-kitoblarga ko‘ra, pilot portfelning 10 foizini qamrab oluvchi bazaviy ssenariyda defolt ehtimolining 0,3 foiz punktga shartli pasayishi kutilayotgan kredit yo‘qotishlarining 14,23 mlrd so‘mga qisqarishiga hamda jami 18,55 mlrd so‘mlik, ya’ni bank kapitalining 0,093 foiziga teng moliyaviy samaraga olib kelishi aniqlangan.Keywords
sun’iy intellekt, kredit qarorlari, kvazieksperiment, farqlar farqi usuli, ehtimollik balli bo‘yicha moslashtirish, tizim uchun ahamiyatli bank, O‘zmilliybank, kutilayotgan kredit yo‘qotishlari, moliyaviy samaradorlik.References
1. Abdurahmonov K. X., Mag‘rupov A. Yu., Zokirova N. K. Raqamli transformatsiya sharoitida inson kapitali va mehnat bozori. – Toshkent, 2024.
2. Abdurashidova M. S., Balbaa M. E. Sun’iy intellektning O‘zbekiston bank tizimidagi istiqbollari // Iqtisodiyot va innovatsion texnologiyalar. – 2024.
3. Bank of England; Financial Conduct Authority. Artificial Intelligence in UK Financial Services – 2024 [Elektron resurs]. – London, 2024. – URL: https://www.bankofengland.co.uk/report/2024/artificial- intelligence-in-uk-financial-services-2024.
4. Callaway B., Sant’Anna P. H. C. Difference-in-Differences with Multiple Time Periods // Journal of Econometrics. – 2021. – Vol. 225, No. 2. – P. 200–230. – DOI: 10.1016/j.jeconom.2020.12.001. – URL: https://doi.org/10.1016/j.jeconom.2020.12.001.
5. Chen B., Guo D., Xia J., Zhang Z. The Transformative Role of Artificial Intelligence and Big Data in Banking [Elektron resurs]. – FDIC Center for Financial Research, 2025. – URL: https://www.fdic.gov/ center-financial-research/transformative-role-artificial-intelligence-and-big-data-banking.pdf. FDIC
6. Financial Stability Board. Artificial Intelligence and Machine Learning in Financial Services: Market Developments and Financial Stability Implications [Elektron resurs]. – Basel: Financial Stability Board, 2017. – URL: https://www.fsb.org/2017/11/artificial-intelligence-and-machine-learning-in-financial-service/.
7. Financial Stability Board. The Financial Stability Implications of Artificial Intelligence [Elektron resurs]. – Basel: Financial Stability Board, 2024. – URL: https://www.fsb.org/2024/11/the-financial-stability- implications-of-artificial-intelligence/.
8. Fuster A., Plosser M., Schnabl P., Vickery J. The Role of Technology in Mortgage Lending // The Review of Financial Studies. – 2019. – Vol. 32, No. 5. – P. 1854–1899. – DOI: 10.1093/rfs/hhz018. – URL: https:// doi.org/10.1093/rfs/hhz018.
9. Gambacorta L., Huang Y., Qiu H., Wang J. How Do Machine Learning and Non-Traditional Data Affect Credit Scoring? New Evidence from a Chinese Fintech Firm. – BIS Working Papers. – 2019. – No. 834. – URL: https://www.bis.org/publ/work834.htm
10. International Accounting Standards Board. IFRS 9 Financial Instruments [Elektron resurs]. – London: IFRS Foundation. – URL: https://www.ifrs.org/issued-standards/list-of-standards/ifrs-9-financial-instruments/.
11. Isaeva M. U. Credit Scoring in Digital Age: Benchmarking Telecom, Card Transactions and Credit History Data // Raqamli iqtisodiyot. – 2025. – 13-son. – B. 1482–1499.
12. O‘zbekiston Respublikasi Markaziy banki. 2026-yil uchun tizim uchun ahamiyatli banklar ro‘yxati [Elektron resurs]. – URL: https://cbu.uz/en/financial-stability/press-releases/2982192/.
13. Rosenbaum P. R., Rubin D. B. The Central Role of the Propensity Score in Observational Studies for Causal Effects // Biometrika. – 1983. – Vol. 70, No. 1. – P. 41–55. – DOI: 10.1093/biomet/70.1.41. – URL: https://doi.org/10.1093/biomet/70.1.41
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 GREEN ECONOMY AND DEVELOPMENT
This work is licensed under a Creative Commons Attribution 4.0 International License.
