Models and Methods for Assessing the Credit-Worthiness of a Corporate Borrower of a Commercial Bank

Risk management is the basis for the functioning of the banking business. For effective risk management, banks need to have accurate banking risk assessment tools. Imperfect systems for assessing credit risks and creditworthiness of bank borrowers are one of the main causes of financial losses and bankruptcies in the banking sector. The purpose of this work is to build a model for assessing the probability of bankruptcy of a corporate borrower of a bank. Tasks set in accordance with the purpose of the work: 1. An analysis of empirical work on the assessment of the creditworthiness of a bank's corporate borrower in order to identify key model parameters 2. The formation of a sample of companies used to determine the coefficients of the model 3. Construction of a model for assessing the probability of bankruptcy and testing on a control sample Based on the results of the analysis, the model based on logistic regression was selected as the final one, which turned out to be the most accurate on the control sample, and used a small number of parameters, which is convenient to use. In addition, several noteworthy patterns were identified. The parameters associated with the amount of short-term debt were one of the most effective in terms of differentiating bankrupt enterprises and financially stable firms. Profitability indicators also demonstrated the ability to serve as indicators of impending bankruptcy. The liquidity level and the parameters corresponding to it also turned out to be significant in assessing the probability of bankruptcy in the framework of this study. It is important to note that a significant part of enterprises went bankrupt despite good financial performance, which affected the accuracy of the models in terms of forecasting default. Companies may go bankrupt for non-economic reasons that cannot be predicted by financial reporting models. To solve this problem, it is necessary to develop other models that are not based on financial statements in order to be able to most effectively assess the creditworthiness of borrowers and manage credit risk.