Multi-Factor Risk Analysis of Modern Fintech based on Multimodal Analytics

The relevance of this study lies in the significance of a thorough examination of the implications of the rapid expansion and widespread adoption of modern financial technologies. The purpose of the study is to identify the characteristics of f intech-related risks using multimodal business analytics which is based on machine learning, neural networks and data mining technologies. Hypothesis. The use of methods and tools for multimodal business analytics based on machine learning and neural networks will ensure the further instrumentalization of risk assessment and analysis of fintech, taking into account multifactoriality, polyvariance and interdependence nature of risks. This will fully reflect the complexity of modern financial technologies and their impact on the transformation of financial and economic relations. Research methods. The study was based on multimodal analytics, which involved the construction of cross-analysis risk matrices, highlighting the mutual decreasing and increasing influence on the interests of participants in financial relations. For a comprehensive assessment, key fintech tools were selected —  cryptocurrencies (as an investment instruments and means of payment), digital financial assets and digital financial services, such as digital transfers. The results of the study showed that modern financial technologies play a key role in transforming the financial sector, making it more accessible, efficient, and customer oriented. It has been stated that the introduction of fintech in Russia contributes to financial inclusion by providing access to financial services for those who were previously excluded from the traditional banking system. Interpretation of multimodal analytics materials has demonstrated that the use of cryptocurrencies for investment and settlements in the Russian Federation is subject to high market and regulatory risks. In the digital financial assets market, issuers face problems of insufficient liquidity, and digital financial services demonstrate vulnerabilities in the f ield of data protection and operational reliability. As a result, we can conclude that the use of multimodal analytics tools integrating various data sources and research methods allows for a deeper understanding and effective assessment of the complex risks associated with modern financial technologies. Based on the results of the study, we propose practice oriented recommendations for improving risk management in the Russian financial technology sector for regulators and other parties involved in financial transactions.

1. Dudin M. N., Shkodinsky S. V. Challenges and threats of the digital economy to the sustainability of the national banking system. Finance: Theory and Practice. 2022;26(6):52–71. DOI: 10.26794/2587–5671–2021-26–6–52–71

2. Aldboush H. H., Ferdous M. Building trust in fintech: An analysis of ethical and privacy considerations in the intersection of Big Data, AI, and customer trust. International Journal of Financial Studies. 2023;11(3):90. DOI: 0.3390/ijfs11030090

3. Zeleneva E. S. Assessment of the characteristics, scopes and limits of the application of digital innovations in the f inancial sector. Finance: Theory and Practice. 2023;27(2):76–86. DOI: 10.26794/2587–5671–2023–27–2–76–8

4. Van Groenendaal W. J.H., Kleijnen J. P.C. On the assessment of economic risk: Factorial design versus Monte Carlo methods. Reliability Engineering & System Safety. 1997;57(1):91–102. DOI: 10.1016/S 0951-8320(97)00019–7

5. Batrancea L. M., Balcı M. A., Akgüller Ö., Gaban L. What drives economic growth across European countries? A multimodal approach. Mathematics. 2022;10(19):3660. DOI: 10.3390/math10193660

6. Sawhney R., Mathur P., Mangal A., Khanna P., Shah R. R., Zimmermann R. Multimodal multi-task financial risk forecasting. In: Proc. 28th ACM Int. conf. on multimedia (Seattle, WA, October 12–16, 2020). New York, NY: Association for Computing Machinery; 2020:456–465. DOI: 10.1145/3394171.3413752

7. Chen Y.-F., Huang S.-H. Sentiment-influenced trading system based on multimodal deep reinforcement learning. Applied Soft Computing. 2021;112:107788. DOI: 10.1016/j.asoc.2021.107788

8. Lee S. I., Yoo S. J. Multimodal deep learning for finance: Integrating and forecasting international stock markets. The Journal of Supercomputing. 2020;76(10):8294–8312. DOI: 10.1007/s11227–019–03101–3

9. Mikhnenko P. A. Multimodal business analytics: The concept and its application prospects in economic science and practice. Upravlenets = The Manager. 2023;14(6):2–18. (In Russ.). DOI: 10.29141/2218–5003-2023–14–6–1

10. Gaw N., Yousefi S., Gahrooei M. R. Multimodal data fusion for systems improvement: A review. IISE Transactions. 2022;54(11):1098–1116. DOI: 10.1080/24725854.2021.1987593

11. Mikhnenko P. A. Transformation of the largest Russian companies’ business vocabulary in annual reports: Data mining. Upravlenets = The Manager. 2022;13(5):17–33. (In Russ.). DOI: 10.29141/2218–5003–2022–13–5–2

12. Mikhnenko P. A. Data-mining as tool of multimodal business-analysis: Lexical transformation in annual reports of Rostech corporation. Vestnik Rossiiskogo ekonomicheskogo universiteta imeni G. V. Plekhanova = Vestnik of the Plekhanov Russian University of Economics. 2022;19(6):126–136. (In Russ.). DOI: 10.21686/2413-2829–2022–6–126–136

13. Kuzmin M. A. Comparative analysis of data analytics approaches in the context of business digital transformation. Uchenye zapiski Rossiiskoi Akademii predprinimatel’stva = Scientific Notes of the Russian Academy of Entrepreneurship. 2024;23(3):19–28. (In Russ.). DOI: 10.24182/2073–6258–2024–23–3–19–28

14. Yudin G. O. Overview of approaches to multimodal business analysis of ESG indicators of the organization. IIASU’23 — Artificial intelligence in automated control and data processing systems. Proc. 2nd All-Russ. sci. conf. (Moscow, April 27–28, 2023). In 5 vols. Vol. 4. Moscow: KDU, Dobrosvet; 2024:93–96. (In Russ.).

15. Gandhi A., et al. Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Information Fusion. 2023;91:424–444. DOI: 10.1016/j.inffus.2022.09.025

16. Kotliarov I. D. Fintech: Nature and models of implementation. EKO: vserossiiskii ekonomicheskii zhurnal = ECO Journal. 2018;(12):23–39. (In Russ.). DOI: 10.30680/EC 00131–7652–2018–12–23–39

17. Menshikov E. I., Konobeeva A. B. Theoretical and practical aspects of digital tools for corporate finance development. Vestnik Moskovskogo finansovo-yuridicheskogo universiteta MFYuA = Herald of the Mosсow University of Finances and Law MFUA. 2021;(4):153–164. (In Russ.). DOI: 10.52210/2224669X_2021_4_153

18. Sokolinskaya N. E., Markova O. M. Fintech services market: State and development trends. Finansovye rynki i banki = Financial Markets and Banks. 2023;(6):117–124. URL: https://cyberleninka.ru/article/n/rynok-fintehuslug-sostoyanie-i-tendentsii-razvitiya (In Russ.).

19. Arun Prakash A., Leelavathi R., Rupashree R., Jisha V. G. Fintech apps: An integral tool in titivating banking operations. In: Naved M., Ajantha Devi V., Gupta A. K., eds. Fintech and cryptocurrency. Hoboken, NJ: John Wiley & Sons, Inc.; 2023:137–155. DOI: 10.1002/9781119905028.ch7

20. Elia G., Stefanelli V., Ferilli G. B. Investigating the role of Fintech in the banking industry: What do we know? European Journal of Innovation Management. 2023;26(5):1365–1393. DOI: 10.1108/EJIM-12–2021–0608

21. Werth O., Cardona D. R., Torno A., Breitner M.H, Muntermann J. What determines FinTech success? — A taxonomy-based analysis of FinTech success factors. Electronic Markets. 2023;33(1):21. DOI: 10.1007/s12525023–00626–7

22. Koshelev K. A. Trends in the evolution of the digital financial assets market in the context of the digital transformation of the global economy. Finance: Theory and Practice. 2022;26(4):80–94. DOI: 10.26794/2587-5671–2022–26–4–80–94

23. Kochergin D. A. Central banks digital currencies for cross-border payments: Interoperability models and implementation possibilities. Finance: Theory and Practice. 2024;28(2):82–100. DOI: 10.26794/2587–5671-2024–28–2–82–100

24. Uzougbo N. S., Ikegwu C. G., Adewusi A. O. International enforcement of cryptocurrency laws: Jurisdictional challenges and collaborative solutions. Magna Scientia Advanced Research and Reviews. 2024;11(1):68–83. DOI: 10.30574/msarr.2024.11.1.0075

25. Peretolchin A. P. Genesis and prospects of development of legal regulation of digital financial assets in the Russian Federation. Journal of Digital Technologies and Law. 2023;1(3):752–774. (In Russ.). DOI: 10.21202/jdtl.2023.33

26. Abuzov A. Yu. Digital financial assets: Essence, types, development in modern conditions. Fundamental’nye issledovaniya = Fundamental Research. 2024;(3):8–13. (In Russ.). DOI: 10.17513/fr.43573