Embedded Predictor Selection for Default Risk Calculation: A Southeast Asian Industry Study

Default risk estimation is a core business of rating agencies. Banks and other financial institutions need to scale the default risk of their counterparties, identifying predictors that significantly contribute to default probability insight into fundamentals of credit risk analysis. Default analysis and predictor selection are two related issues, but many existing approaches address them separately. A unified procedure is employed, a regularization approach based on the GLM model, which allows simultaneously selecting the default predictors and optimizes all the parameters within the model. For this purpose Lasso and elastic-net penalty functions are employed as regularization terms. The methods are applied to predict default of companies from the industry sector in Southeast Asian countries. The relevant default predictors over the countries reveal that credit risk analysis is sample specific. The empirical result shows that the proposed method has a very high accuracy of default prediction.

[1]  Andrew W. Lo,et al.  Logit versus discriminant analysis : A specification test and application to corporate bankruptcies , 1986 .

[2]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

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

[4]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[5]  Edward I. Altman,et al.  Corporate Financial Distress and Bankruptcy: Predict and Avoid Bankruptcy, Analyze and Invest in Distressed Debt , 2005 .

[6]  W. Beaver.  Financial Ratios As Predictors Of Failure , 1966 .

[7]  Marjorie B. Platt,et al.  BANKRUPTCY DISCRIMINATION WITH REAL VARIABLES , 1994 .

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

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

[10]  D. Hand,et al.  A k-nearest-neighbour classifier for assessing consumer credit risk , 1996 .

[11]  S. Sathiya Keerthi,et al.  A simple and efficient algorithm for gene selection using sparse logistic regression , 2003, Bioinform..

[12]  Edward I. Altman,et al.  Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience) , 1994 .

[13]  Edward I. Altman,et al.  FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY , 1968 .

[14]  Melody Y. Kiang,et al.  Managerial Applications of Neural Networks: The Case of Bank Failure Predictions , 1992 .

[15]  Wolfgang Härdle,et al.  Modeling default risk with support vector machines , 2011 .

[16]  Trevor J. Hastie,et al.  Genome-wide association analysis by lasso penalized logistic regression , 2009, Bioinform..

[17]  A. Lau.  A 5-State Financial Distress Prediction Model , 1987 .

[18]  Wolfgang K. Härdle,et al.  The Bayesian Additive Classification Tree Applied to Credit Risk Modelling , 2008, Comput. Stat. Data Anal..

[19]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[20]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[21]  Sofie Balcaen,et al.  35 years of studies on business failure: an overview of the classic statistical methodologies and their related problems , 2006 .

[22]  Dedy Dwi Prastyo,et al.  Support Vector Machines with Evolutionary Feature Selection for Default Prediction , 2012 .

[23]  K. Lange,et al.  Coordinate descent algorithms for lasso penalized regression , 2008, 0803.3876.

[24]  Andreas Christmann,et al.  Support vector machine , 2013 .

[25]  Yuh-Jye Lee,et al.  Variable selection and oversampling in the use of smooth support vector machines for predicting the default risk of companies , 2009 .

[26]  Ji Zhu,et al.  Boosting as a Regularized Path to a Maximum Margin Classifier , 2004, J. Mach. Learn. Res..