Credit Risk Measurement of Trusted Customers Using Logistic Regression and Neural Networks
Subject Areas : Business StrategyGholamreza Khojasteh 1 , Saeed Daei Karimzadeh 2 , Hossein Sharifi Ranani 3
1 - Department of Management, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
2 - Department of Economics, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
3 - Department of Economics, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
Keywords: Receiver Operating Characteristic (ROC), Credit Risk, Neural Networks, Logistic regression,
Abstract :
The issue of credit risk and deferred bank claims is one of the sensitive issues of banking industry, which can be considered as the main cause of bank failures. In recent years, the economic slowdown accompanied by inflation in Iran has led to an increase in deferred bank claims that could put the country's banking system in serious trouble. Accordingly, the current paper presents a prediction model for credit risk of real customers of Qavamin Bank Branch in Shiraz, using a combined approach of logistic regression and neural network. Therefore, the necessary examinations were carried out on a sample of 351 individuals from the real customers of the bank in the period 2011-2012. According to the information available, 17 variables were extracted including financial and non-financial variables for classifying customers into well-balanced s and ill-balanced s. Among the variables, five effective variables on credit risk were selected using the parent forward stepwise selection technique, which was used to train neural networks with three neurons in the hidden layer. the optimum cutting point was selected based on the performance curve of the system and the results of the neural network output on the test data show that the accuracy of the combined model in the classifier of well-balanced customers is .89 and in the category of ill-balanced customers is .83 that is better than the results of logistic regression and in general, it is possible to estimate the accuracy of prediction.
Abdoli, Ghahreman and Fard Hariri, Alireza (2015). "Modeling the Risk Assessment of Legal Customers of the Bank of Rafah" Journal of Applied Economics Theory, Second Year, No. 1, pp. 1-24.
Arab Mazar, Abbas and Royan Tan, Puneh (2006). "Factors Affecting Credit Risk of Bank Customers, Case Study of Agricultural Bank". Economic research, 3 (6), 45-80.
Beikzadeh, Jafar and Aghazadeh, Gholamreza and Aghazadeh, Mohammad Reza (2014) "The Study of Factors Affecting Credit Risk and Prioritizing Credit Scoring Criteria (C-6) for Bank Customers Using AHP Technique, Case Study of West Azarbayjan Bank", Ravand Quarterly, No. 68, pp. 121-150.
Baharloo, Nahid, Ali Akbar Amin Bidokhti and Javad Mohaghegh Nia (2015). "Comparison of Optimal Model of Multiple and Binary Logistic Regression for Credit Rating of Real Customers of Rafah Kargaran Bank", Journal of Economic Research, No. 63, pp. 147-166.
Ghassemi, Ahmad Reza, Tahereh Deniyayi (2015), "Customer Credit Risk Measurement with Neural Network Approach in a Government Bank", Financial Engineering and Management of Securities, No. 27, pp. 155- 181.
Hosseini, Abdolkhalagh and Zibaee, Mansour (2014) "Credit Risk Management in Agricultural Bank of Mamasani City Using Neural Network Model", Journal of Agricultural Economics, No. 2, pp. 111-119.
Jamei, Reza; Ahmadi, Fereydoun and Nasiri, Behnam. (2015). "Credit risk assessment of banking customers' classification using multi-criteria prediction and decision models (Case study: National Bank of Kurdistan Province)". Accounting Reviews 3 (9). 81-108.
Ja'fari, Eskandari, Meysam, Roohi and Roohi Milad. (2017). "Banking Credit Risk Management for Bank Customers Using the Decision Makers Method with Genetic Algorithm with Data Mining Approach." Asset Management and Financing, 5 (4), 17-32i.
Karimi, Zahra and Asadi Gorji, Hossein and Gilak Hakim Abadi, Mohammad Taghi and Asadi, Norahla (2015). "Factors Affecting Credit Risk of Customers of Commercial Banks Case Study: Bank of Commerce of Neka City - Mazandaran Province" Quarterly Journal of Monetary Economics, Finance, No. 10, pp. 205-234.
Kia, Mostafa, (2010), "Neural Networks in MATLAB", Tehran, Kian Rayaneh Green Publishing, Third Edition.
Mirzaei, Hossein and Nazarian, Rafik and Bagheri, Rana (2011) "Investigating the Factors Affecting Credit Risk of Legal Persons of Banks (Case Study of the National Bank of Iran, Tehran), Quarterly Journal of Economic Research, Vol. 19, No. 58, Pp. 67-98.
Rahmani, Ali and Gharibe Esmaeili (2010), Efficiency of Neural Networks, Logistic Regression, and Differentiation Analysis in Prognosis of Default, Economics of Value, No. 4, pp. 151-172.
Salehi, Mojtaba; Kurd Kutuli, Alireza. (2017). "Choosing the best features to determine the credit risk of bank customers." Smart Business Management Studies 6 (22) .124-1594.
Tehrani, Reza and Shams, Fallah (2005) "Designing and explaining the model of credit risk in the banking system of the country", Journal of Social Sciences and Humanities, Shiraz University, Vol. 22, No. 2, pp. 45-60.