Subject. Scoring systems with artificial intelligence as a factor of stability and sustainability of lending in financial institutions. Objectives. To conduct a comparative analysis of the financial indicators of scoring systems incorporating neural network technologies with traditional bank borrower assessment systems, and, on this basis, to determine the opportunities and necessity of using artificial intelligence systems in credit institutions. Methods. The total cost of ownership method was used, along with methods of logical, comparative, and statistical analysis. Results. A comprehensive and multifaceted analysis of the development of neural network technologies in financial institutions was carried out. An assessment of the global market for these technologies was provided. The impact of neural network technologies on the profits of financial institutions was analyzed. The main areas of application of artificial intelligence in the financial sector were examined. The use of neural network technologies in bank scoring systems – which help to significantly reduce risks in loan issuance – was analyzed. The effectiveness of the implemented scoring systems with neural network technologies was evaluated. A model for assessing the effectiveness of a borrower evaluation system based on the total cost method was proposed; it allows comparing the costs of implementing a traditional scoring system with those of a system using artificial intelligence. Conclusions. The obtained results can be applied by Russian banking institutions to provide a comprehensive justification for the implementation of scoring systems with artificial intelligence in the practice of borrower assessment during loan issuance.
Keywords: management, information technology, digital economy, neural network technologies, scoring systems
References:
Koroleva E. Attitude towards using FinTech services: Digital immigrants versus digital natives. International Journal of Innovation and Technology Management, 2022, vol. 19, no. 8, 2250029. DOI: 10.1142/S0219877022500298 EDN: CJRJQW
Arbatskaia D.E., Rodionov D.G., Ungvari L., Konnikov E.A. [Comparative analysis of approaches to modeling changes in the financial markets of the technological sector of the economy]. Myagkie izmereniya i vychisleniya, 2024, vol. 74, no. 1‑1, pp. 71–82. (In Russ.) DOI: 10.36871/2618-9976.2024.01.007 EDN: AQCNCR
Ahmad A.Y.B.A., Tiwari A., Nayeem M.A. et al. Artificial Intelligence Perspective Framework of the Smart Finance and Accounting Management Model. International Journal of Intelligent Systems and Applications in Engineering, 2024, vol. 12, no. 4, pp. 586–594.
Lyukevich I., Agranov A., Lvova N., Guzikova L. Digital experience: How to find a tool for evaluating business economic risk. International Journal of Technology, 2020, vol. 11, no. 6, pp. 1244–1254. DOI: 10.14716/ijtech.v11i6.4466 EDN: CIFTFA
Apsilyam N.M., Shamsudinova L.R., Yakhshiboyev R.E. The application of artificial intelligence in the economic sector. Central Asian Journal of Education and Computer Sciences (CAJECS), 2024, vol. 3, no. 1, pp. 1–12.
Koroleva E. FinTech entrepreneurial ecosystems: Exploring the interplay between input and output. International Journal of Financial Studies, 2022, vol. 10, iss. 4. DOI: 10.3390/ijfs10040092 EDN: WJVKBN
Sidorin A.A., Polyakova A.A., Dudareva A.B., Kozhanchikova N.Yu. [Improved methods of assessing the creditworthiness of potential borrowers]. Russian Journal of Agricultural and Socio‑Economic Sciences, 2017, no. 7, pp. 102–107. (In Russ.) DOI: 10.18551/rjoas.2017-07.11 EDN: XPXHTV
Abdullaev N.A. [Prospects for the implementation of modern technologies of artificial intelligence in scoring systems]. Ekonomika i finansy (Uzbekistan), 2023, no. 1, pp. 39–49. (In Russ.) DOI: 10.34920/EIF/VOL_2023_ISSUE_1_6 EDN: LELIED
Ten V.V. [Problems of analyzing the borrower’s creditworthiness]. Bankovskoe delo, 2006, no. 3, pp. 49–51. (In Russ.) EDN: HTWPRT
Gorelaia N.V. [Assessment of the borrower’s creditworthiness in the credit risk management system]. Upravlenie korporativnymi finansami, 2005, no. 6, pp. 30–41. (In Russ.) EDN: HUXGHV
Rodionov D.G., Konnikov E.A., Mugutdinov R.M. [System analysis of a digital enterprise competitiveness within the information environment]. Ekonomicheskie nauki, 2020, no. 193, pp. 394–401. (In Russ.) DOI: 10.14451/1.193.394 EDN: WBMKJQ
Huang Z., Che C., Zheng H., Li C. Research on Generative Artificial Intelligence for Virtual Financial Robo‑Advisor. Academic Journal of Science and Technology, 2024, vol. 10, no. 1, pp. 74–80. DOI: 10.54097/30r2kk80 EDN: WZLWWV
Giudici P., Centurelli M., Turchetta S. Artificial Intelligence risk measurement. Expert Systems with Applications, 2024, vol. 235, 121220. DOI: 10.1016/j.eswa.2023.121220 EDN: EYDHEQ
Akour I., Alzyoudb M., Alquqa E.K. et al. Artificial intelligence and financial decisions: Empirical evidence from developing economies. International Journal of Data and Network Science, 2024, vol. 8, pp. 101–108. DOI: 10.5267/j.ijdns.2023.10.013 EDN: WHLGYH
Rodionov D., Koshelev E., Van Lo.T.H. Model of cross‑financing for research and development costs in a federal district. Sustainable Development and Engineering Economics, 2023, iss. 2, pp. 24–38. DOI: 10.48554/SDEE.2023.2.2 EDN: LFOVZE
Hidayat M., Defitri S.Yu., Hilman H. The Impact of Artificial Intelligence (AI) on Financial Management. Management Studies and Business Journal (PRODUCTIVITY), 2024, vol. 1, no. 1, pp. 123–129. DOI: 10.62207/s298rx18 EDN: EEPHTH
Ivanov V.V., Lvova N.A., Saksonova S., Lyukevich I.N. Digital accessibility in the context of preference for financial services. Petersburg University Journal of Economic Studies, 2023, vol. 39, no. 2, pp. 179–197. DOI: 10.21638/spbu05.2023.202 EDN: XUJACI
Egorov I.A., Kondratiev V.Yu. [Total cost of ownership (TCO) analysis methodology]. Innovatsii i investitsii, 2022, no. 11, pp. 183–187. (In Russ.) EDN: NJBWZV
