Financial Soundness Prediction Using a Multi-classification Model: Evidence from Current Financial Crisis in OECD Banks

The paper aims to develop an early warning model that separates previously rated banks (337 Fitch-rated banks from OECD) into three classes, based on their financial health and using a one-year window. The early warning system is based on a classification model which estimates the Fitch ratings using Bankscope bank-specific data, regulatory and macroeconomic data as input variables. The authors propose a “hybridization technique” that combines the Extreme learning machine and the Synthetic Minority Over-sampling Technique. Due to the imbalanced nature of the problem, the authors apply an oversampling technique on the data aiming to improve the classification results on the minority groups. The methodology proposed outperforms other existing classification techniques used to predict bank solvency. It proved essential in improving average accuracy and especially the performance of the minority groups.

[1]  Ignacio Olmeda,et al.  Hybrid Classifiers for Financial Multicriteria Decision Making: The Case of Bankruptcy Prediction , 1997 .

[2]  Vadlamani Ravi,et al.  Bankruptcy prediction in banks and firms via statistical and intelligent techniques - A review , 2007, Eur. J. Oper. Res..

[3]  A. Demirguç-Kunt,et al.  The Determinants of Banking Crises in Developing and Developed Countries , 1998 .

[4]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[5]  T. Beck,et al.  A New Database on the Structure and Development of the Financial Sector , 2000 .

[6]  David C. Wheelock,et al.  Why do Banks Disappear? The Determinants of U.S. Bank Failures and Acquisitions , 2000, Review of Economics and Statistics.

[7]  Huiling Chen,et al.  An Effective Computational Model for Bankruptcy Prediction Using Kernel Extreme Learning Machine Approach , 2017 .

[8]  James R. Barth,et al.  Bank Regulations are Changing: For Better or Worse? , 2008 .

[9]  Zexuan Zhu,et al.  A fast pruned-extreme learning machine for classification problem , 2008, Neurocomputing.

[10]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Gokhan Torna,et al.  Nontraditional Banking Activities and Bank Failures During the Financial Crisis , 2013 .

[12]  Amaury Lendasse,et al.  Bankruptcy prediction using Extreme Learning Machine and financial expertise , 2014, Neurocomputing.

[13]  Stijn Claessens,et al.  The Political Economy of Distress in East Asian Financial Institutions , 2000 .

[14]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[15]  P. Cashin,et al.  The Anatomy of Banking Crises , 2008, SSRN Electronic Journal.

[16]  Pedro Antonio Gutiérrez,et al.  Hybridizing logistic regression with product unit and RBF networks for accurate detection and prediction of banking crises , 2010, Omega.

[17]  James R. Barth,et al.  The Regulation and Supervision of Banks around the World: A New Database , 2001 .

[18]  Mikhail V. Oet,et al.  Early Warning Systems for Systemic Banking Risk: Critical Review and Modeling Implications , 2010 .

[19]  Constantin Zopounidis,et al.  Assessing Bank Soundness with Classification Techniques , 2009 .

[20]  Pedro Antonio Gutiérrez,et al.  A dynamic over-sampling procedure based on sensitivity for multi-class problems , 2011, Pattern Recognit..

[21]  Anna J. Schwartz,et al.  A Monetary History of the United States, 1867-1960. , 1964 .

[22]  T. Beck,et al.  Bank concentration, competition, and crises: First results , 2006 .

[23]  Arturo Estrella,et al.  Capital Ratios as Predictors of Bank Failure , 2000 .

[24]  Daniel Martin,et al.  Early warning of bank failure: A logit regression approach , 1977 .

[25]  Daniel Porath.  Estimating Probabilities of Default for German Savings Banks and Credit Cooperatives , 2006 .

[26]  Martin Weber,et al.  Loan Growth and Riskiness of Banks , 2010 .

[27]  You-Shyang Chen,et al.  A soft-computing based rough sets classifier for classifying IPO returns in the financial markets , 2012, Appl. Soft Comput..

[28]  Samuel H. Szewczyk,et al.  Bond rating agencies and their role in bank market discipline , 1992 .

[29]  A. Sironi.  Testing for Market Discipline in the European Banking Industry: Evidence from Subordinated Debt Issues , 2000 .

[30]  Georgios Chortareas,et al.  Bank supervision, regulation, and efficiency: evidence from the European Union , 2012 .

[31]  James B. Thomson,et al.  Predicting bank failures in the 1980s , 1991 .

[32]  Edward S. O'Neal,et al.  The cost of market versus regulatory discipline in banking 1 We thank Allen Berger, David Brown, Ric , 1998 .

[33]  A. Rose,et al.  Cross-Country Causes and Consequences of the 2008 Crisis: Early Warning , 2012 .

[34]  I. Hasan,et al.  Financial Crises and Bank Failures: A Review of Prediction Methods , 2009 .

[35]  A. Richards,et al.  Rating Agency Actions and the Pricing of Debt and Equity of European Banks: What Can We Infer About Private Sector Monitoring of Bank Soundness? , 2001, SSRN Electronic Journal.

[36]  Brenda González-Hermosillo,et al.  Determinants of Ex-Ante Banking System Distress: A Macro-Micro Empirical Exploration of Some Recent Episodes , 1999, SSRN Electronic Journal.

[37]  E. Davis,et al.  Comparing early warning systems for banking crises , 2008 .

[38]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[39]  G. Ferri,et al.  The Political Economy of Bank Distress: Evidence from East Asia , 2001 .

[40]  Stephen Kwek,et al.  Applying Support Vector Machines to Imbalanced Datasets , 2004, ECML.

[41]  C. Lindgren,et al.  Bank Soundness and Macroeconomic Policy , 1996 .

[42]  M. Friedman,et al.  A Monetary History of the United States , 1963 .

[43]  César Hervás-Martínez,et al.  PCA-ELM: A Robust and Pruned Extreme Learning Machine Approach Based on Principal Component Analysis , 2012, Neural Processing Letters.

[44]  Pedro Antonio Gutiérrez,et al.  Sensitivity Versus Accuracy in Multiclass Problems Using Memetic Pareto Evolutionary Neural Networks , 2010, IEEE Transactions on Neural Networks.

[45]  Melody Y. Kiang,et al.  Predicting Bank Failures: A neural network approach , 1990, Appl. Artif. Intell..

[46]  Constantin Zopounidis,et al.  A multicriteria decision framework for measuring banks' soundness around the world , 2006 .

[47]  Asli Demirgüç-Kunt,et al.  The Determinants of Banking Crises: Evidence from Industrial and Developing Countries , 1997 .

[48]  Nellie Liang.  Bank profits, risk, and local market concentration , 1989 .

[49]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[50]  Asli Demirgüç-Kunt,et al.  Banking on the Principles: Compliance with Basel Core Principles and Bank Soundness , 2006, SSRN Electronic Journal.

[51]  Amaury Lendasse,et al.  OP-ELM: Optimally Pruned Extreme Learning Machine , 2010, IEEE Transactions on Neural Networks.

[52]  R. Billings,et al.  Determinants of Banking System Fragility: A Case Study of Mexico , 1997 .

[53]  Asli Demirgüç-Kunt,et al.  Inside the Crisis: An Empirical Analysis of Banking System in Distress , 1999, SSRN Electronic Journal.