Evaluation of Financial Fragility Using Neural Networks

Document Type : Research Paper

Author

Ph.D. in Economics, Researcher, Banking Research Group

Abstract

Predicting continuation of the activity of a bank for future periods is an important element in the decision-making process by bank supervisors. The choice of the appropriate method and variable to predict is the main challenging problem in the literature of predicting financial fragility. The neural network model is one of the most advanced predictive models of financial fragility. In the sample under study, using theoretical and empirical literature, financial fragility index is defined according to the structure of the banking network of Iran. Then, the significance of financial ratios is tested using t-test and mean of two samples is tested at 95% confidence level applying Levin statistic. Then, a neural network model is designed with inclusion of significant explanatory financial ratios. To test the accuracy of the model, the classification table and a Receiver Operating Characteristic (ROC) curve is used. Results show that the predictive power of the model is 96%. According to the findings of this paper, credit risk and liquidity risk are the most important explanatory factors of financial fragility.

Keywords

References

منابع 
 -        کاظمی، ابوالفضل؛ قاسمی، جواد و زندیه، وحید. (1390). رتبه‌بندی اعتباری مشتریان حقیقی بانک‌ها با استفاده از مدل‌های مختلف شبکه‌های عصبی: مطالعه موردی یکی از بانک‌های خصوصی ایران. مطالعات مدیریت صنعتی. سال نهم، شماره 33، زمستان 90: 161-131.
-        کیا، مصطفی. (1389). شبکه‌های عصبی در MATLAB. انتشارات کیان رایان سبز، چاپ سوم.
-        صورت مالی بانک‌های کشور (93-1385)، مؤسسه عالی بانکداری ایران.
-        دادمحمدی، دانیال و احمدی، عباس. (1393). رتبه‌بندی اعتباری مشتریان بانک با استفاده از شبکه عصبی با اتصالات جانبی. فصلنامه توسعه مدیریت پولی و بانکی، سال دوم، شماره 3، تابستان.
-        محرابیان، سعید؛ ساعتی مهتدی، صابر و هادی، علی. (1390). ارزیابی کارآیی شعب بانک اقتصاد نوین با ترکیبی از روش شبکه عصبی و تحلیل پوششی داده‌ها. مجله تحقیق در عملیات و کاربردهای آن، سال هشتم، شماره4 (پیاپی 31)، زمستان 90: 39-29.
-        نماگرهای اقتصادی، 93-1385، بانک مرکزی ایران.
-        Andrianova, S., Baltagi, B., Lensik, R., Rewilak, J., & Rousseau, P. (2015). A New International Database on Financial Fragility. University of Leicester, Department of Economics, Working paper, No. 15/18.
-        Caprio, G., & Klingebiel, D.C. (2002). Episodes of systemic and borderline banking crises. In: D. Klingebiel and L. Laeven, eds., Managing the Real and Fiscal Effects of Banking Crises. Washington, D. C. The World Bank, Discussion Paper, No. 428: 31-49.
-        Degryse, H., & Elahi, M. A. (2012). Determinants of banking system fragility: A regional perspective. Katholieke universiteit Leuven. Faculty of Business Economics. Working paper: AFI_1263.
-        Demirguc-Kunt, A., & Detragiache, E. (1998). The Determinants of Banking Crises: Evidence from Developed and Developing Countries. Working Paper, The World Bank.
-        Ecer, F. (2013). Comparing the bank failure prediction performance of neural networks and support vector machines: the Turkish case. Economic research, 26(3), 81-98.
-        Erdal, H. I., & Ekinci, A. (2013). A comparison of various artificial intelligence methods in the prediction of bank failures. Computational Economics, 42(2), 199-215.
-        Fielding, D., & Rewilak, J. (2015). Credit booms, financial fragility and banking crises. Economics Letters, 136, 233-236.
-        Geluk, J., de Haan, L., & de Vries, C. (2007). Weak & Strong Financial fragility. Tinbergen Institute Discussion Paper, The Erasmus Universiteit Rotterdam, No: 023/2
-        Ghosh, S. (2011). A simple index of banking fragility: application to Indian data. The Journal of Risk Finance, 12(2), 112-120.
-        Hashemi, R. R., Le Blanc, L. A., Rucks, C. T., & Rajaratnam, A. (1998). A hybrid intelligent system for predicting bank holding structures. European Journal of Operational Research, 109(2), 390-402.
-        Hawkins, J., & M. Klau. (2000). Measuring potential vulnerabilities in emerging market economies. Basel: Bank for International Settlements, Working papers, No. 91.
-        Khemakhem, S., & Boujelbene, Y. (2015). Credit risk prediction: A comparative study between discriminant analysis and the neural network approach. Accounting and Management Information Systems, 14(1), 60-78.
-        Kibritcioglu, A. (2002). Excessive risk-taking, banking sector fragility, and banking crises. U of Illinois, Commerce and Bus. Admin. Working Paper, (02-0114).
-        Lindgren, C. J., Garcia, G. G., & Saal, M. I. (1996). Bank soundness and macroeconomic policy. International Monetary Fund.
-        Messai, A. S., & Gallali, M. I. (2015). Financial Leading Indicators of Banking Distress: A Micro Prudential Approach-Evidence from Europe. Asian Social Science, 11(21), 78.
-        Odom, M. D., & Sharda, R. (1990). A neural network model for bankruptcy prediction. In 1990 IJCNN International Joint Conference on neural networks (pp. 163-168).
-        Penas, M. F., & Tümer-Alkan, G. (2010). Bank disclosure and market assessment of financial fragility: evidence from Turkish banks’ equity prices. Journal of financial services research, 37(2-3), 159-178.
-        Pesola, J. O. (2007). Financial fragility, macroeconomic shocks and bank’s loan losses: evidence from Europe. Social Science Research Network electronic library. http://ssrn.com/abstract_id=1018637. 
-        Tadesse, S. (2005). Banking fragility and disclosure: international evidence. University of South Carolina.
-        Wanke, P., Azad, M. A. K., & Barros, C. P. (2016). Predicting efficiency in Malaysian Islamic banks: A two-stage TOPSIS and neural networks approach. Research in International Business and Finance, 36, 485-498.
-        Zaghdoudi, T. (2013). Bank failure prediction with logistic regression. International Journal of Economics and Financial Issues, 3(2), 537-543.
-        Zhang, W., Cao, Q., & Schniederjans, M. J. (2004). Neural network earnings per share forecasting models: a comparative analysis of alternative methods. Decision Sciences, 35(2), 205-237.
-        Zwet, A. V., & Swank, J. (2000). Financial Fragility and Macroeconomic Performance. De Nederlandsche Bank: DNB Staff Reports, 2000, No. 52.
 
 
 

Files

Share

How to cite

Statistics