Development of Methods to Enhance the Effectiveness of the Organization’s Monetary Policy

This research considers topical issues of increasing the efficiency of credit policy in enterprises and organizations operating under difficult conditions. These conditions are marked by high volatility in key parameters of the external business environment and a significant decrease in the financial stability and solvency of many businesses. Based on the analysis of the mechanism for forming the credit policy of business entities, the authors conclude that the most important components of such a mechanism, directly determining its overall efficiency, are the assessment of the creditworthiness of potential debtors of the enterprise and the impact of the enterprise’s credit policy on its core business. To enhance the efficiency of the credit policy framework, the research suggests utilizing the random forest method of machine learning to model the business behavior of potential debtors. Improving the management of accounts receivable and payable is especially relevant in the context of the high volatility of the external environment and reduced financial stability of enterprises. The research primarily focuses on analyzing the mechanisms for developing credit policies within enterprises and identifying the key components that influence their effectiveness. These components include assessing the creditworthiness of debtors, evaluating the impact of credit policy on the core activities of the enterprise, and incorporating machine learning methods. Using the random forest method makes it possible to increase the efficiency of assessing the business behavior of debtors and minimizing financial risks. The research methodology includes general scientific methods and theoretical and empirical approaches. The research findings have been practically applied in developing an algorithm for assessing the creditworthiness of debtors using the random forest method, accompanied by a step-by-step implementation guide.