This study proposes an Artificial Intelligence (AI) and Machine Learning (ML)–based approach to strengthen internal controls in credit institutions. The research develops multivariable regression models to predict key financial metrics, such as profit, revenue, capital, and liabilities, using the residual sum of squares optimization method. A target function is formulated by integrating these predictive models with dependencies derived from financial reports of credit organizations, with the objective of optimizing this function. Furthermore, potential asset vulnerabilities are identified by analyzing the minimum values of Return on Assets (ROA), Return on Equity (ROE), and net profit. The solution space focuses on selecting ROA and ROE combinations where the profit-to-income ratio remains within the dynamic range of 0 to 1, rather than targeting a fixed value. The models demonstrate strong predictive performance, with an average adjusted R2 of 89.77% and an average deviation below 10.22%, confirming the model's robustness. Practical validity is supported through case studies of Armenian credit institutions, showing compliance with target financial ratios under varying constraints.
Babayan et al. (Sat,) studied this question.