The Comparison of Applying a Designed Model to Measure Credit Risk Between Melli and Mellat Banks

The main purpose of this paper is providing a model tocalculate the credit risk of Melli bank clients and implement it atMellat Bank. Therefore, the present study uses a multi-layeredneural network method. The statistical population of this researchis all real and legal clients of Melli and Mellat banks. Samplingmethod used in this research is a simple random sampling method.Friedman test was used to calculate the required number ofsamples in a random sampling method from Cochran formula(1977) and Friedman test was used to rank the factors affecting thecredit risk. Friedman test was also performed using data from acompleted questionnaire of active experts at the Melli Bank. Basedon the results obtained from Friedman test, five important factorsin the credit risk of real clients of the Melli Bank of Iran, type of occupation, guarantee value, loan amount, having return checks,the balance average, and the value of the guarantee, the amount ofthe loan, the average of the balance, having returned checks anddeferred loans are the most important factors affecting the creditrisk of legal clients, which have been used as inputs in the neuralnetwork model. The results of credit risk prediction using theneural network showed that the designed model has a high abilityto predict the credit risk of real and legal clients of the Melli bank,while it did not have this ability for the Mellat bank.