Financial innovation: Credit default hybrid model for SME lending

We propose an ANN/logistic credit risk hybrid model for SME lending.We find that the hybrid model is more accurate than either of the separate ones.Our study is one of few that sheds light on the hybrid model.Our study is one of few which focuses on credit risk models for SMEs.The hybrid model can help the bank decrease the errors in credit risk evaluations. Credit risk evaluation is an integral part of any lending process, and even more so for financial institutions involved in lending to SMEs. The importance of credit scoring has increased recently because of the financial crisis and increased capital requirements for banks. There are, however, only few studies that develop credit coring models for SME lending. The objective of this study is to introduce a novel, more accurate credit risk estimation approach for SMEs business lending. Based on traditional statistical methods and recent artificial intelligence (AI) techniques, we proposed a hybrid model which combines the logistic regression approach and artificial neural networks (ANN). In order to test the effectiveness and feasibility of the proposed hybrid model, we use the data of Finnish SMEs from the fiscal years 2004 to 2012. Our results suggest that the proposed ANN/logistic hybrid model is more accurate than either of the initial models ANN or logistic regression. This improvement in the accuracy of the credit scoring model decreases evaluation errors and has thereby many potential practical implications. First of all, a more accurate credit scoring model can result in better performance of the whole SME loan portfolio. Second, it can also result in lower capital requirements from the banks perspective and lower interest rates from the individual firm's perspective. Combined, these effects will enhance the banks competitiveness in the market for SME loans.

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

[2]  Jasmina Arifovic,et al.  Using genetic algorithms to select architecture of a feedforward artificial neural network , 2001 .

[3]  D. Hensher,et al.  Predicting Firm Financial Distress: A Mixed Logit Model , 2004 .

[4]  Jesper Lindé,et al.  Credit Risk Versus Capital Requirements Under Basel Ii: Are SME Loans and Retail Credit Really Different? , 2004 .

[5]  OreskiStjepan,et al.  Hybrid system with genetic algorithm and artificial neural networks and its application to retail credit risk assessment , 2012 .

[6]  Jonathan Crook,et al.  Scoring by usage , 2001, J. Oper. Res. Soc..

[7]  R. Malhotra,et al.  Evaluating Consumer Loans Using Neural Networks , 2001 .

[8]  M. Dietsch,et al.  Should SME exposures be treated as retail or corporate exposures? A comparative analysis of default probabilities and asset correlations in French and German SMEs , 2004 .

[9]  Selwyn Piramuthu,et al.  Financial credit-risk evaluation with neural and neurofuzzy systems , 1999, Eur. J. Oper. Res..

[10]  Jalal D. Akhavein,et al.  The Diffusion of Financial Innovations: An Examination of the Adoption of Small Business Credit Scoring by Large Banking Organizations , 2001 .

[11]  Vijay S. Desai,et al.  A comparison of neural networks and linear scoring models in the credit union environment , 1996 .

[12]  Hussein A. Abdou,et al.  On the applicability of credit scoring models in Egyptian banks , 2007 .

[13]  David C. Ewert.  TRADE‐CREDIT MANAGEMENT: SELECTION OF ACCOUNTS RECEIVABLE USING A STATISTICAL MODEL , 1968 .

[14]  Terry Harris,et al.  Credit scoring using the clustered support vector machine , 2015, Expert Syst. Appl..

[15]  Vaclav Kozeny.  Genetic algorithms for credit scoring: Alternative fitness function performance comparison , 2015, Expert Syst. Appl..

[16]  Hossein Etemadi,et al.  A Genetic Programming Model for Bankruptcy Prediction: Empirical Evidence from Iran , 2009, Expert Syst. Appl..

[17]  R. Malhotra,et al.  Evaluating Consumer Loans using Neural Networks , 2003 .

[18]  Terence C. Fogarty,et al.  Evolving Bayesian classifiers for credit control—a comparison with other machine-learning methods , 1993 .

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

[20]  James H. Myers,et al.  The Development of Numerical Credit Evaluation Systems , 1963 .

[21]  Stjepan Oreski,et al.  Hybrid system with genetic algorithm and artificial neural networks and its application to retail credit risk assessment , 2012, Expert Syst. Appl..

[22]  ChenMu-Chen,et al.  Credit scoring with a data mining approach based on support vector machines , 2007 .

[23]  Ali Zeinal Hamadani,et al.  AN INTEGRATED GENETIC -BASED MODEL OF NAIVE BAYES NETWORKS FOR CREDIT SCORING , 2013 .

[24]  Daniel Enache,et al.  Analyzing Credit Risk Data: A Comparison of Logistic Discrimination, Classification Tree Analysis, a , 1997 .

[25]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[26]  Bart Baesens,et al.  Comprehensible Credit Scoring Models Using Rule Extraction from Support Vector Machines , 2007, Eur. J. Oper. Res..

[27]  David J. Hand,et al.  Statistical Classification Methods in Consumer Credit Scoring: a Review , 1997 .

[28]  A. Steenackers,et al.  A credit scoring model for personal loans , 1989 .

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

[30]  Monty L. Lynn,et al.  Development of a Prediction Model for Hospital Closure Using Financial Accounting Data , 1993 .

[31]  Ekrem Duman,et al.  Detecting credit card fraud by Modified Fisher Discriminant Analysis , 2015, Expert Syst. Appl..

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

[33]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[34]  Armando Blanco,et al.  A real-coded genetic algorithm for training recurrent neural networks , 2001, Neural Networks.

[35]  Shu Ling Lin,et al.  A new two-stage hybrid approach of credit risk in banking industry , 2009, Expert Syst. Appl..

[36]  Jodi L. Gissel,et al.  A Review of Bankruptcy Prediction Studies: 1930 to Present , 2006 .

[37]  W. Hopwood,et al.  A Reexamination of Auditor versus Model Accuracy within the Context of the Going-Concern Opinion Decision* , 1994 .

[38]  Adnan Khashman,et al.  Credit risk evaluation using neural networks: Emotional versus conventional models , 2011, Appl. Soft Comput..

[39]  Samprit Chatterjee,et al.  A Nonparametric Approach to Credit Screening , 1970 .

[40]  Derya Soydaner,et al.  Artificial Neural Networks with Gradient Learning Algorithm for Credit Scoring , 2015 .

[41]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[42]  Hussein A. Abdou,et al.  Credit Scoring, Statistical Techniques and Evaluation Criteria: A Review of the Literature , 2011, Intell. Syst. Account. Finance Manag..

[43]  A M Walker,et al.  Prediction and cross-validation of neural networks versus logistic regression: using hepatic disorders as an example. , 1998, American journal of epidemiology.

[44]  Deron Liang,et al.  The effect of feature selection on financial distress prediction , 2015, Knowl. Based Syst..

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

[46]  Dennis L. Hoffman,et al.  An econometric analysis of the bank credit scoring problem , 1989 .

[47]  Diana Adler,et al.  Using Multivariate Statistics , 2016 .

[48]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[49]  Andrea Roli,et al.  A neural network approach for credit risk evaluation , 2008 .

[50]  Jonathan N. Crook,et al.  Recent developments in consumer credit risk assessment , 2007, Eur. J. Oper. Res..

[51]  Naeem Siddiqi,et al.  Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring , 2005 .

[52]  William D. Berry,et al.  Multiple regression in practice , 1985 .

[53]  Byeong Ho Kang,et al.  Investigation and improvement of multi-layer perception neural networks for credit scoring , 2015, Expert Syst. Appl..

[54]  Rebel A. Cole,et al.  The Importance of Relationships to the Availability of Credit , 1998 .

[55]  Yair E. Orgler.  A Credit Scoring Model for Commercial Loans , 1970 .

[56]  Stjepan Oreski,et al.  Genetic algorithm-based heuristic for feature selection in credit risk assessment , 2014, Expert Syst. Appl..

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

[58]  Feng-Chia Li,et al.  Combination of feature selection approaches with SVM in credit scoring , 2010, Expert Syst. Appl..

[59]  Michael Y. Hu,et al.  Forecasting with artificial neural networks : The state of the art * , 1997 .

[60]  Jonathan Crook,et al.  Support vector regression for loss given default modelling , 2015, Eur. J. Oper. Res..

[61]  Jesper Lindé,et al.  Credit Risk Versus Capital Requirements under Basel II: Are SME Loans and Retail Credit Really Different? , 2005 .

[62]  Johan A. K. Suykens,et al.  Benchmarking state-of-the-art classification algorithms for credit scoring , 2003, J. Oper. Res. Soc..

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

[64]  N. Šarlija,et al.  Multinomial model in consumer credit scoring , 2005 .

[65]  David J. Hand,et al.  Discriminant analysis when the classes arise from a continuum , 1998, Pattern Recognit..

[66]  Chih-Fong Tsai,et al.  Using neural network ensembles for bankruptcy prediction and credit scoring , 2008, Expert Syst. Appl..

[67]  Mukta Paliwal,et al.  Neural networks and statistical techniques: A review of applications , 2009, Expert Syst. Appl..