Factors Affecting Credit Risk Management of Legal Bankers Using Logit Regression Model and Maximum Likelihood Method

Abstract

This research was carried out with the aim of identifying effective factors and developing a model for assessing the credit risk of legal clients of the Mellat Bank of Semnan province by "Logit Regression" method. For this purpose, qualitative and financial information of a random sample of 200 companies that had received credit facilities from the Mellat Bank Branch of Semnan Province during 2009-2010 was investigated. In this study, after examining the credit records of each sample, 36 explanatory variables including qualitative and financial variables were identified and examined. Among the existing variables, using Logit Regression analysis, 17 variables that have a significant effect on credit risk and the separation between the two groups of happy and ignorant customers, were chosen and the final model was fitted with them. According to statistical indices, these functions have significant and high validity in terms of coefficients and separation power.