Bankruptcy Prediction in Banks by Principal Component Analysis Threshold Accepting trained Wavelet Neural Network Hybrid

This paper proposes new principal component analysis-wavelet neural network hybrid (PCA-TAWNN) architecture trained by Threshold Accepting (TA) algorithm to predict bankruptcy in banks. This architecture consists of an input layer, the principal component layer consisting of a few selected principal components, a hidden layer with wavelet activation function and finally an output layer with a sigmoid activation function. The effectiveness of PCA-TAWNN is tested on Turkish, Spanish and UK banks bankruptcy datasets and two benchmark datasets Wine and WBC. We observed that PCA-TAWNN convincingly outperformed other techniques in terms of Area under ROC curve (AUC) in 10-fold cross-validation.

[1]  Ingoo Han,et al.  A case-based reasoning with the feature weights derived by analytic hierarchy process for bankruptcy prediction , 2002, Expert Syst. Appl..

[2]  P. Ravikumar,et al.  Bankruptcy Prediction in Banks by an Ensemble Classifier , 2006, 2006 IEEE International Conference on Industrial Technology.

[3]  Vadlamani Ravi,et al.  Soft computing system for bank performance prediction , 2008, Appl. Soft Comput..

[4]  Serpil Canbas,et al.  Prediction of commercial bank failure via multivariate statistical analysis of financial structures: The Turkish case , 2005, Eur. J. Oper. Res..

[5]  Vadlamani Ravi,et al.  Threshold accepting trained principal component neural network and feature subset selection: Application to bankruptcy prediction in banks , 2008, Appl. Soft Comput..

[6]  Sungzoon Cho,et al.  Bankruptcy prediction for credit risk using an auto-associative neural network in Korean firms , 2003, 2003 IEEE International Conference on Computational Intelligence for Financial Engineering, 2003. Proceedings..

[7]  Gordon V. Karels,et al.  Multivariate Normality and Forecasting of Business Bankruptcy , 1987 .

[8]  Vadlamani Ravi,et al.  A Semi-Online Training Algorithm for the Radial Basis Function Neural Networks: Applications to Bankruptcy Prediction in Banks , 2008 .

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

[10]  Vadlamani Ravi,et al.  Failure prediction of banks using threshold accepting trained kernel principal component neural network , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[11]  Vadlamani Ravi,et al.  Non-linear principal component analysis-based hybrid classifiers: an application to bankruptcy prediction in banks , 2010, Int. J. Inf. Decis. Sci..

[12]  Mik Wisniewski,et al.  Applied Regression Analysis: A Research Tool , 1990 .

[13]  Vadlamani Ravi,et al.  Modified Great Deluge Algorithm based Auto Associative Neural Network for Bankruptcy Prediction in Banks , 2007 .

[14]  Vadlamani Ravi,et al.  Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks , 2009, Expert Syst. Appl..

[15]  Rebel A. Cole,et al.  A CAMEL Rating's Shelf Life , 1995 .

[16]  Ramesh Sharda,et al.  A neural network model for bankruptcy prediction , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[17]  Ramesh Sharda,et al.  Bankruptcy prediction using neural networks , 1994, Decis. Support Syst..

[18]  Hui Li,et al.  Financial distress prediction based on serial combination of multiple classifiers , 2009, Expert Syst. Appl..

[19]  Vadlamani Ravi,et al.  Bankruptcy Prediction in Banks by Fuzzy Rule Based Classifier , 2007, 2006 1st International Conference on Digital Information Management.

[20]  D. G. Morrison,et al.  Financial Ratios , Discriminant Analysis and the Prediction of Corporate Bankruptcy , 2016 .

[21]  Roberto Kawakami Harrop Galvão,et al.  Neural and Wavelet Network Models for Financial Distress Classification , 2005, Data Mining and Knowledge Discovery.

[22]  Chi-Bin Cheng,et al.  Financial distress prediction by a radial basis function network with logit analysis learning , 2006, Comput. Math. Appl..

[23]  Manuel Landajo,et al.  Forecasting business profitability by using classification techniques: A comparative analysis based on a Spanish case , 2005, Eur. J. Oper. Res..

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

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

[26]  Thomas E. McKee.  Developing a bankruptcy prediction model via rough sets theory , 2000, Intell. Syst. Account. Finance Manag..

[27]  B. Ahn,et al.  The integrated methodology of rough set theory and artificial neural network for business failure prediction , 2000 .

[28]  Kyung-shik Shin,et al.  A genetic algorithm application in bankruptcy prediction modeling , 2002, Expert Syst. Appl..

[29]  Ingoo Han,et al.  Bankruptcy prediction using case-based reasoning, neural networks, and discriminant analysis , 1997 .

[30]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[31]  Kar Yan Tam,et al.  Neural network models and the prediction of bank bankruptcy , 1991 .

[32]  Hui Li,et al.  Majority voting combination of multiple case-based reasoning for financial distress prediction , 2009, Expert Syst. Appl..

[33]  Hui Li,et al.  Listed companies' financial distress prediction based on weighted majority voting combination of multiple classifiers , 2008, Expert Syst. Appl..

[34]  Vadlamani Ravi,et al.  Feature selection and fuzzy rule-based classifier applied to bankruptcy prediction in banks , 2009, Int. J. Inf. Decis. Sci..

[35]  Koen Vanhoof,et al.  Bankruptcy prediction using a data envelopment analysis , 2004, Eur. J. Oper. Res..

[36]  M. Beynon,et al.  Variable precision rough set theory and data discretisation: an application to corporate failure prediction , 2001 .

[37]  Jeffrey A. Clark,et al.  Off-site monitoring systems for predicting bank underperformance: a comparison of neural networks, discriminant analysis, and professional human judgment , 2001, Intell. Syst. Account. Finance Manag..

[38]  Young U. Ryu,et al.  Firm bankruptcy prediction: experimental comparison of isotonic separation and other classification approaches , 2005, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[39]  Vadlamani Ravi,et al.  Support vector machine and wavelet neural network hybrid: application to bankruptcy prediction in banks , 2010, Int. J. Data Min. Model. Manag..

[40]  Vadlamani Ravi,et al.  Privacy preservation in data mining using hybrid perturbation methods: an application to bankruptcy prediction in banks , 2009, Int. J. Data Anal. Tech. Strateg..

[41]  E. Mine Cinar,et al.  Neural Networks: A New Tool for Predicting Thrift Failures , 1992 .

[42]  Amir F. Atiya,et al.  Bankruptcy prediction for credit risk using neural networks: A survey and new results , 2001, IEEE Trans. Neural Networks.

[43]  Timothy B. Bell,et al.  Neural nets or the logit model? A comparison of each model's ability to predict commercial bank failures , 1997, Intell. Syst. Account. Finance Manag..

[44]  James A. Ohlson.  FINANCIAL RATIOS AND THE PROBABILISTIC PREDICTION OF BANKRUPTCY , 1980 .

[45]  David E. Booth,et al.  The use of fuzzy clustering algorithm and self-organizing neural networks for identifying potentially failing banks: an experimental study , 2000 .

[46]  Kyung-shik Shin,et al.  An application of support vector machines in bankruptcy prediction model , 2005, Expert Syst. Appl..

[47]  Hiok Chai Quek,et al.  GenSo-EWS: a novel neural-fuzzy based early warning system for predicting bank failures , 2004, Neural Networks.