Applying a nonparametric random forest algorithm to assess the credit risk of the energy industry in China

Abstract With the rapid growth of the credit card business in China's energy industry, credit risk is gradually revealed. This study aims to scientifically measure the credit risk of credit cards used in China's energy industry and to lay the foundation for comprehensive credit risk management. Based on an analysis of the factors influencing credit risk influencing factors, this study applies the random forest algorithm and the monthly data of credit cards used by energy industry customers in a branch of the Postal Savings Bank of China from April 2014 to June 2017 to build an effective credit risk assessment model and scientifically measure the credit risk in China's energy industry. The results suggest that credit card features like the overdraft ratio and the amount of credit card expenses within a month have significant impacts on credit risk, our model's comprehensive prediction accuracy is as high as 91.5%, and its stability is satisfying. These findings can provide valuable information to help banks improve their credit risk management.

[1]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[2]  David D. Williams,et al.  Cash Flow in Bankruptcy Prediction , 1987 .

[3]  David West,et al.  Neural network credit scoring models , 2000, Comput. Oper. Res..

[4]  E. Altman,et al.  Modelling Credit Risk for SMEs: Evidence from the U.S. Market , 2007 .

[5]  J. Wiginton.  A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior , 1980, Journal of Financial and Quantitative Analysis.

[6]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[7]  Tin Kam Ho,et al.  The Random Subspace Method for Constructing Decision Forests , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  C. Selvi,et al.  A Study of Dimensionality Reduction Techniques with Machine Learning Methods for Credit Risk Prediction , 2017 .

[9]  Sheng-Tun Li,et al.  The evaluation of consumer loans using support vector machines , 2006, Expert Syst. Appl..

[10]  Paulius Danenas,et al.  Selection of Support Vector Machines based classifiers for credit risk domain , 2015, Expert Syst. Appl..

[11]  Bernard Micha,et al.  Analysis of business failures in France , 1984 .

[12]  Maheshwar Dwivedy,et al.  Using Functional Link Artificial Neural Network (FLANN) for Bank Credit Risk Assessment , 2017 .

[13]  R. Lussier.  A Nonfinancial Business Success versus Failure Prediction Model for Young Firms , 1995 .

[14]  Laurent Heutte,et al.  Using Random Forests for Handwritten Digit Recognition , 2007, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).

[15]  E. Altman,et al.  ZETATM analysis A new model to identify bankruptcy risk of corporations , 1977 .

[16]  Bart Baesens,et al.  Using Neural Network Rule Extraction and Decision Tables for Credit - Risk Evaluation , 2003, Manag. Sci..

[17]  James H. Scott.  The probability of bankruptcy: A comparison of empirical predictions and theoretical models , 1981 .

[18]  S. J. Press,et al.  Choosing between Logistic Regression and Discriminant Analysis , 1978 .

[19]  So Young Sohn,et al.  Technology credit scoring model with fuzzy logistic regression , 2016, Appl. Soft Comput..

[20]  Vural Aksakalli,et al.  Risk assessment in social lending via random forests , 2015, Expert Syst. Appl..

[21]  Dean Fantazzini,et al.  Random Survival Forests Models for SME Credit Risk Measurement , 2009 .

[22]  M. Chijoriga,et al.  Application of multiple discriminant analysis (MDA) as a credit scoring and risk assessment model , 2011 .

[23]  Nazeeh Ghatasheh,et al.  Business Analytics using Random Forest Trees for Credit Risk Prediction: A Comparison Study , 2014 .

[24]  Mark Schreiner,et al.  Scoring Arrears at a Microlender in Bolivia , 2004 .

[25]  Efraim Turban,et al.  Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real-World Performance , 1992 .

[26]  Hussein A. Abdou,et al.  Neural nets versus conventional techniques in credit scoring in Egyptian banking , 2008, Expert Syst. Appl..

[27]  Mu-Chen Chen,et al.  Credit scoring with a data mining approach based on support vector machines , 2007, Expert Syst. Appl..

[28]  Hiroyuki Mori,et al.  Credit risk evaluation in power market with random forest , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[29]  Ralf Stecking,et al.  Support vector machines for classifying and describing credit applicants: detecting typical and critical regions , 2005, J. Oper. Res. Soc..

[30]  Edward C. Lawrence,et al.  Forecasting losses on a liquidating long-term loan portfolio , 1995 .

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

[32]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001 .

[33]  Saulius Gudas,et al.  Credit Risk Evaluation Model Development Using Support Vector Based Classifiers , 2011, ICCS.

[34]  Nasser Mohammadi,et al.  Customer Credit Risk Assessment using Artificial Neural Networks , 2016 .

[35]  Michiko Miyamoto,et al.  Credit Risk Assessment for a Small Bank by Using a Multinomial Logistic Regression Model , 2014 .

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

[37]  Kenneth A. Carow,et al.  Debit, credit, or cash: survey evidence on gasoline purchases , 1999 .