Iranian Financial Engineering Association(IFEA) International Journal of Finance & Managerial Accounting 2588-4379 1 3 2016 10 01 Forecasting Credit Risk in Banks Listed on Tehran Stock Exchange 29 45 9903 EN Ammar Feyzi Young Researchers and Elites Club ,Saveh branch ,Islamic azad university ,Saveh ,iran. Mohammadreza Ghorbanian Faculty Member, Department of Accounting, University of Shahre-Ghods, Tehran, Iran. Valalioalah Berangi PH.D Business Administration International Tendencies, Islamic Azad University Science and Research Branch of Tehran, Instructor at Islamic Azad University, Central Tehran Branch, Iran Journal Article 2016 02 01 <span style="color: black; line-height: 115%; font-family: 'Times New Roman','serif'; font-size: 9pt; mso-themecolor: text1; mso-fareast-font-family: Calibri; mso-fareast-theme-font: minor-latin; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;">The present study aim is to offer a systematic method of assessing the credit risk of banks and also to identify key indicators using Decision Making Trial and Evaluation Laboratory (DEMATEL) technique as well as using Logit Regression in order to predict the credit risk of listed banks. The population of the study consists of the legal clients of the bank (Ansar Bank, Bank Saderat Iran, Bank Mellat, Parsian Bank, Bank Pasargad, Post Bank of Iran, Tejarat Bank, Sina Bank, Krafarin Bank, and Eghtesad Novin Bank), who have been granted facilities. The results of the study show that, implementing DEMATEL technique, the variable of asset turnover ratio is the most influential indicator among the examined indicators in predicting the credit risk of banks. In addition, the variables of cash ratio, free cash flow ratio, and current ratio are among the most effective variables, respectively, and the current ratio is the indicator mostly affected compared to other indicators. And according to the prediction made by Logit Model, 207 of the 276 clients, who were prompt in paying their dues, have been categorized properly. This indicates 70% of the dependent variables (y =0) have been predicted properly. Furthermore, 100 of the 176 clients, who were delinquent in paying dues, have been categorized properly. This means that 57% of the variables (y=1) have been predicted properly</span> http://www.ijfma.ir/article_9903_d93c96e6a23fff65b91b900aaa541998.pdf