A hybrid model for estimating the probability of default of corporate customers

Document Type : Research Paper


1 Faculty of Management, University of Tehran

2 Faculty of Management and Accounting, Shahid Beheshti Universit


Credit risk estimation is a key determinant for the success of financial institutions. The aim of this paper is presenting a new hybrid model for estimating the probability of default of corporate customers in a commercial bank. This hybrid model is developed as a combination of Logit model and Neural Network to benefit from the advantages of both linear and non-linear models. For model verification, this study uses an experimental dataset collected from the companies listed in Tehran Stock Exchange for the period of 2008–2014. The estimation sample included 175 companies, 50 of which were considered for model testing. Stepwise and Swapwise least square methods were used for variable selection. Experimental results demonstrate that the proposed hybrid model for credit rating classification outperform the Logit model and Neural Network. Considering the available literature review, the significant variables were gross profit to sale, retained earnings to total asset, fixed asset to total asset and interest to total debt, gross profit to asset, operational profit to sale, and EBIT to sale.


Main Subjects

Article Title [فارسی]

ارائة مدل ترکیبی برآورد احتمال نکول مشتریان حقوقی بانک‌ها

Authors [فارسی]

  • رضا راعی 1
  • مهدی سعیدی کوشا 1
  • سعید فلاح پور 1
  • محمد فدائی نژاد 2
1 دانشکده مدیریت ،دانشگاه تهران
2 دانشکده مدیریت و حسابداری، دانشگاه شهید بهشتی
Abstract [فارسی]

تخمین ریسک اعتباری یکی از معیارهای کلیدی در موفقیت بانک یا مؤسسة اعتباری است. هدف این مقاله ارائة مدلی ترکیبی برای تخمین احتمال نکول مشتریان حقوقی در بانک‌های تجاری است. این مدل ترکیبی از ترکیب مدل لوجیت و شبکة عصبی توسعه یافته است که باعث استفاده از مزایای مدل خطی و غیرخطی به‌صورت هم‌زمان می‌شود. برای تأیید مدل از داده‌های شرکت‌های بورسی در دورة زمانی 1387 تا 1392 استفاده شده است که حجم نمونة 175 شرکت بوده است که 125 داده برای مدل‌سازی و 50 داده به عنوان داده‌های برون نمونه‌ای برای تست مدل استفاده شده‌اند. برای انتخاب متغیرهای از روش حداقل مربعات قدم به قدم (پیش‌رونده- پس‌رونده) استفاده شده است. نتایج نشان می‌دهد مدل ترکیبی جدید از مدل لوجیت و شبکة عصبی بهتر عمل می‌کند. برخلاف تحقیقات گذشته، متغیرهای اثرگذار عبارت است از سود ناخالص به فروش، سود انباشته به دارایی، دارایی ثابت به کل دارایی، بهره به کل بدهی، سود ناخالص به دارایی، سود عملیاتی به فروش و سود قبل از بهره و مالیات به فروش.

Keywords [فارسی]

  • ریسک اعتباری
  • شبکة عصبی
  • مدل ترکیبی
  • مدل لوجیت
  • نکول
Akkoc, S. (2012).An empirical comparison of conventional techniques, neural networks and the three stage hybrid adaptive neuro-fuzzy inference system (ANFIS) model for credit scoring analysis: the case of Turkish credit card data. European Journal of Operational Research, 222(1), 168–178.
Al-Kassar, T., Soileau, J. (2014).Financial performance evaluation and bankruptcy prediction (failure).ARAB ECONOMICS AND BUSINESS JOURNAL, 9(2), 147–155.
Altman, E.I., Marco, G., Varetto, F. (1994). Corporate distress diagnosis: comparisons using linear discriminant analysis and Neural Networks (the Italian experience). Journal of Banking and Finance, 18(3), 505-529.
Altman, I.E. (1968).Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4), 589-609.
Altman, I.E. and Narayanan, P. (1997).An international survey of business failure classification models. Financial Markets, Institutions & Instruments, 6 (2), 1-57.
Angelini, E., Tollo, G., Roli, A. (2008). A Neural Network approach for credit risk evaluation. The Quarterly Review of Economics and Finance, 48(4), 733-755.
Aziz, M.A., Dar, H.A. (2006). Predicting corporate bankruptcy: where we stand?. Corporate Governance: The International Journal of Effective Board Performance, 6 (1), 18-33.
Beaver, W.H. (1966).Financial ratios as predictors of failure. Journal of Accounting Research, 4 (3), 71-111.
Bekhet, H., Eletter, S. (2014). Credit risk management for the Jordanian commercial banks: Neural scoring approach. Review of Development Finance, 4, 20–28.
Bell, T., Ribar, G., Verchio, J. (1990). Neural nets versus logistic regression: A comparison of each model's ability to predict commercial bank failures: Proceedings of the 1990 Deloitte & Touche/University of Kansas Symposium on Auditing Problems, 029-053.
Cao, Q., Parry, M. (2009). Neural Network earning per share forecasting models: a comparison of backward propagation and genetic algorithm. Decision Support Systems, 47, 32–41.
Casey, C.J. and Bartczak, N.J. (1984).Cash flow – it’s not the bottom line, Harvard Business Review, July-August, 61-66.
Chen, M., Huang, S. (2003). Credit scoring and rejected instances reassigning through evolutionary computation techniques. Expert Systems with Applications, 24, 433–441.
Chen, Y., Cheng, C. (2013).Hybrid models based on rough set classifiers for setting credit rating decision rules in the global banking industry. Knowledge-Based Systems, 39, 224–239.
Courtis, J.K. (1978).Modeling a financial ratio categorical framework. Journal of Business Finance and Accounting, 5 (4), 371-86.
Curram, S., Mingers, J. (1994). Neural Networks, Decision tree induction and discriminant analysis: an empirical comparison. Operational Research Society, 45 (4), 440-450.
Dimitras, A.I., Zanakis, S.H. and Zopounidis, C. (1996).A survey of business failures with an emphasis on prediction methods and industrial applications. European Journal of Operational Research, 90 (3), 487-513.
Durand, D. (1941). Risk Elements in Consumer Instalment Financing. National Bureau of Economic Research, New York.
Efroymson, M.A. (1960).Multiple Regression Analysis. Mathematical Methods for Digital Computers, John Wiley, New York.191-203.
Eletter, S. (2012). Using data mining for an intelligent marketing campaign. Global Business and Economics Anthology, 2, 276–282.
Emel, A., Oral, M., Reisman, A., Yolalan, R. (2003).A credit scoring approach for the commercial banking sector. Socio-Economic Planning Sciences, 37 (2), 103–123.
Gestel, T.V., Baesens, B., Dijcke, P.V., Suykens, J.A.K., Garcia, J., Alderweireld, T. (2005). Linear and non-linear credit scoring by combining logistic regression and support vector machines. Journal of Credit Risk, 1 (4), 31-60.
Hand, D. J., and Henley, W. E. (1997). Statistical classification methods in consumer risk. Journal of the Royal Statistical Society, Series A, 160, 523–41.
Haykin, S., 1999. Neural Networks: A Comprehensive Foundation, second ed. Prentice Hall Int. Inc., New Jersey.
Heiat, A. (2012). Comparing performance of data mining models for computer credit scoring. Journal of International Finance & Economics, 12 (1), 78–83.
Hocking, R.R. (1976).The analysis and selection of variables in linear regression. Biometrics, 32, 1-49.
Jones, S., Hensher, D. (2004).Predicting Firm Financial Distress: A Mixed Logit Model. The Accounting Review, 79 (4), 1011-1038.
Kaminski, K.A., Wetzel, T.S. and Guan, L. (2004). Can financial ratios detect fraudulent financial reporting? Managerial Auditing Journal, 19 (1), 15-28.
Kankaanpää, M., Laitinen, T. (1999). Comparative analysis of failure prediction methods: the Finnish case. The European Accounting Review, 8 (1), 67-92.
Khandani, A., Kim, A., Lo, A. (2010). Consumer credit-risk models via machine learning algorithms. Journal of Banking and Finance, 34, 2767–2787.
Lahsasna, A., Ainon, R., Wah, T. (2010). Credit scoring models using soft computing methods: a survey. International Arab Journal of Information Technology, 7 (2), 115–123.
Lee, T., Chiu, C., Lu, C., Chen, I. (2002).Credit scoring using the hybrid neural discriminant technique. Expert Systems with Applications. 23 (3), 245–254.
Lee, T.S., Chen, I.F. (2005).A two-stage hybrid credit scoring model using artificial Neural Networks and multivariate adaptive regression splines. Expert Systems with Applications, 28, 743–752.
McKee, T.E., Lensberg, T. (2002).Genetic programming and rough sets: a hybrid approach to bankruptcy classification. European Journal of Operational Research, 138, 436-51.
Mossman, C. E., Bell, G. G., Turtle, H., Swartz, L. M. (1998). An empirical comparison of bankruptcy models. The Financial Review, 33, 35-54.
Paliwal, M., Kumar, U. (2009). Neural Networks and statistical techniques: a review of applications. Expert Systems with Applications, 36 (1), 2–17.
Persons, O.S. (1995).Using financial statement data to identify factors associated with fraudulent financial reporting. Journal of Applied Business Research, 11 (3), 38-46.
Piramuthu, S. (1999).Financial credit-risk evaluation with neural and neuro-fuzzy systems. European Journal of Operational Research, 112, 310–321.
Premachandra, I.M., Bhabra, G.S., Sueyoshi, T. (2009). DEA as a tool for bankruptcy assessment: A comparative study with logistic regression technique. European Journal of Operational Research, 193, 412–424.
Thomas, L. (2000). A survey of credit and behavioral scoring: forecasting financial risk of lending to consumers. International Journal of Forecasting, 16, 149–172.
Thomas, L., Edelman, D., Crook, J. (2002).Credit Scoring and its Applications. Philadelphia, PA: Society for Industrial and Application Mathematics.
Trippi, R.R., Turban, E. (1996). Neural Networks in Finance and Investing. Irwin Professional Pub., Chicago.
Tsai, C.F., Wu, J.W. (2008). Using Neural Network ensembles for bankruptcy prediction and credit scoring. Expert Systems with Applications, 34, 2639–2649.
Vuran, B. (2009). Prediction of business failure: a comparison of discriminant and logistic regression analyses. İstanbul Üniversitesi İşletmeFakültesiDergisi, 38 (1), 47-65.
West, D. (2000). Neural Network credit scoring models. Computers and Operations Research, 27, 1131–1152.
West, D., Dellana, S., Qian, J. (2005). Neural Network ensemble strategies for financial decision applications. Computers and Operations Research, 32, 2543–2559.
Wilcox, J.W. (1971). A simple theory of financial ratios as predictors of failure. Journal of Accounting Research, 9, 389-95.
Wu, C., Guo, Y., Zhang, X., Xia, H. (2010). Study of personal credit risk assessment based on support vector machine ensemble. International Journal of Innovative, 6 (5), 2353–2360.
Yalsin, N., Bayrakdaroglu, A., Kahraman, C. (2012). Application of fuzzy multi-criteria decision making methods for financial performance evaluation of Turkish manufacturing industries. Expert Systems with Applications, 39, 350–364.
Yap, P., Ong, S., Husain, N. (2011).Using data mining to improve assessment of credit worthiness via credit scoring models. Expert Systems with Applications, 38 (10), 1374–1383.