APPLICATION OF ARTIFICIAL INTELLIGENCE METHODS IN THE BANK RISK MANAGEMENT SYSTEM

Abstract

This article analyzes the main factors affecting the financial efficiency and return on capital of commercial banks based on an econometric approach and substantiates the prospects for the use of artificial intelligence technologies in improving the bank's risk management system. The study took ROE as the outcome indicator, and the impact of the volume of digital banking operations, the country's GDP, the number of users of digital services, and the level of problem loans on it was estimated using a multifactor logarithmic regression model. The empirical results confirmed that digitalization processes and macroeconomic growth have a positive effect on bank profitability, while problem loans have a negative effect. Model diagnostics showed a normal distribution of balances, ensuring statistical reliability of the assessments. It also highlighted the advantages of artificial intelligence methods based on machine learning, neural networks, and "big data" analysis in reducing credit risks, early detection of the probability of default, and increasing operational efficiency. The results of the study show that the introduction of innovative risk management mechanisms in banks enhances financial stability and competitiveness.