THE ROLE OF ARTIFICIAL INTELLIGENCE IN AUTOMATING FINANCIAL ANALYSIS OF ENTERPRISES

EDN: OMJENU

DOI: https://doi.org/10.65891/2949-1983-2026-22-3-15-19

Authors:

KOLOS Igor Viktorovich, SKIBENKO Galina Gennadyevna,

FAYZULAYEVA Zarina Alisherovna

Affiliation:

Federal State Budgetary Educational Institution of Higher Education "Donetsk National University of Economics and Trade named after Mikhail Tugan-Baranovsky" (Donetsk)

Abstract.

This study examines the role of artificial intelligence technologies as a key factor in transforming financial analysis systems in modern enterprises. Specific examples justify the need to move from simple fixation of past performance to a model of continuous predictive monitoring in the context of unstable market conditions. The process of systematization of main areas of automation of financial functions, including introduction of machine learning algorithms (XGBoost, LSTM) for more accurate profit forecasting and use of NLP methods to analyze unstructured data. Special attention is paid in the material to comparative analysis of digital platforms available on the Russian market under modern conditions. The study identified a direct link between the level of adoption of generative AI and the speed of quality management decisions. The result of the study was that it was confirmed a significant economic impact from the use of intelligent systems, expressed in optimization of labor costs of analysis unit and reduction of payback time of IT-infrastructure investments. However, the article identifies barriers that prevent large-scale implementation of AI tools: the problem of opaqueness of the conclusions of complex models («black box») and the risk of reducing the accuracy of forecasts in times of crisis. The formulated conclusions provide a basis for assessing the maturity of analytical systems and determine the vectors for further adaptation of domestic BI solutions to the requirements of RAS in the context of the digital transformation of the economy.

Keywords:

financial analysis, artificial intelligence, business analytics, predictive modeling, machine learning, digital transformation, automation of financial function, BI solutions, NLP, RAS

References:

1. Denisenko, M.P. Information Support for Effective Enterprise Management / M.P. Denisenko, I.V. Kolos // Innovations. 2018. No. 7. Pp. 19–24.
2. Dolya, E.A. The Essence and Conceptual Foundations of Digital Analytics / E.A. Dolya // Trade and Market. – 2023. – No. 2(66). – Pp. 16–24. – EDNOSTSFI.
3. Kazakova, N. A. Financial Analysis: a textbook and workshop for universities / N. A. Kazakova. – 2nd ed., revised and expanded. – Moscow: Yurayt Publishing House, 2026. – 490 p. – Text: electronic // Yurayt Educational Platform [website]. – URL: https://urait.ru/bcode/589126 (accessed: 18.04.2026).
4. Savitskaya, G. V. Comprehensive Analysis of the Enterprise’s Economic Activity: a textbook / G. V. Savitskaya. – 7th ed., revised and expanded. – Moscow: INFRA‑M, 2025. – 608 p. – (Higher Education). – DOI 10.12737/13326. – ISBN 978-5-16-018752-5. – Text: electronic. – URL: https://znanium.ru/catalog/product/2184922 (accessed: 18.04.2026).
5. McKinsey Technology Trends Outlook 2022. – Text: electronic // mckinsey.com: [website]. – URL: https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-top-trends-in-tech-2022#/ (accessed: 18.04.2026).
6. Chen, T. XGBoost: A Scalable Tree Boosting System / T. Chen. – Text: electronic // researchgate.net: [website]. – URL: https://www.researchgate.net/publication/310824798_XGBoost_A_Scalable_Tree_Boosting_System (accessed: 18.04.2026).
7. Providing diagnostics of stock market patterns using artificial intelligence tools / I. V. Kolos, G. G. Skibenko, E. Yu. Tomashevskaya, D. V. Shchetinina // Economics: Theory and Practice. – 2024. – No. 2(74). – Pp. 37–43. – DOI 10.31429/2224042X_2024_74_37. – EDN CKWYWQ.
8. Kolos, I. V. The effectiveness of AI models in predicting the financial performance of enterprises / I. V. Kolos, G. G. Skibenko, D. S. Zaznoba // , November 28, 2025. Vol. 2, 2025. – Pp. 20–25. – EDN HXXSTM.
9. Hariom, T. Beyond the Black Box: Interpretability of LLMs in Finance / T. Hariom. – Text: electronic // arxiv.org: [website]. – URL: https://arxiv.org/abs/2505.24650 (accessed: 18.04.2026).
10. Deloitte, Development. Digital Transformation Tops CFO Priorities for 2026: Signals Survey / Development Deloitte. – Text: electronic // deloitte.wsj.com: [website]. – URL: https://deloitte.wsj.com/cfo/digital-transformation-tops-cfo-priorities-for-2026-signals-survey-14f2562c (accessed: 18.04.2026).
11. PwC: Revisioning Finance in a New Era for Global Business Services. – Text: electronic. – URL: https://www.absl.pl/en/news/p/pwc-revisioning-finance-new-era-global-business-services (accessed: 18.04.2026).
12. Information support for an organization’s management system: textbook / A. V. Rubtsov, S. V. Mamaeva, L. N. Khramova, I. V. Khramov – Krasnoyarsk: Siberian Federal University, 2022. – 111 p.
13. 1C:Analytics | Advanced business analytics tools – the 1C platform:Company. – URL: https://v8.1c.ru/platforma/1s-analitika/ (accessed: 18.04.2026).
14. Constellation BI 2025. – Text: electronic // tedo.ru: [website]. – URL: https://tedo.ru/insights/bi-2025 (accessed: 18.04.2026).
15. Enterprise Performance Management | Oracle. – URL: https://www.oracle.com/performance-management/ (accessed: 18.04.2026).