Credit Risk Analysis Applying Logistic Regression, Neural Networks and Genetic Algorithms Models

Credit models are useful to evaluate the risk of consumer loans. The application of the technique with greater precision of a prediction model will provide financial returns to the institution. In this study a sample set of applicants from a large Brazilian financial institution was focused on in order to develop three models each one based on one of the alternative techniques: Logistic Regression, Neural Networks and Genetic Algorithms. Finally, the quality and performance of these models are evaluated and compared to identify the best one. Results obtained by the logistic regression and neural network models are good and very similar, although the former is slightly better. The genetic algorithm model is also efficient, but somewhat inferior. This study illustrates the procedures to be adopted by a financial institution in order to identify the best credit model to evaluate the risk of consumer loans and thereby get increasing profits.

[1]  Mu-Chen Chen,et al.  Credit scoring and rejected instances reassigning through evolutionary computation techniques , 2003, Expert Syst. Appl..

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

[3]  Sudhir Nanda,et al.  Linear models for minimizing misclassification costs in bankruptcy prediction , 2001, Intell. Syst. Account. Finance Manag..

[4]  Eric R. Ziegel,et al.  An Introduction to Generalized Linear Models , 2002, Technometrics.

[5]  Sebastian Fritz,et al.  Restructuring the credit process: behaviour scoring for german corporates , 2000, Intell. Syst. Account. Finance Manag..

[6]  L. Thomas A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers , 2000 .

[7]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[8]  Soushan Wu,et al.  Credit rating analysis with support vector machines and neural networks: a market comparative study , 2004, Decis. Support Syst..

[9]  Limsoon Wong,et al.  DATA MINING TECHNIQUES , 2003 .

[10]  V. Barnett,et al.  Applied Linear Statistical Models , 1975 .

[11]  Fernando J. Von Zuben,et al.  Support vector machines, inferencia transdutiva e o problema de classificação , 2002 .

[12]  Ali Zilouchian,et al.  FUNDAMENTALS OF NEURAL NETWORKS , 2001 .

[13]  Arquiteturas de Redes Neurais Aplicadas a Data Mining no Mercado Financeiro Uma Aplicao para a Gerao de Credit Ratings , 2016 .

[14]  Lalit M. Patnaik,et al.  Application of genetic programming for multicategory pattern classification , 2000, IEEE Trans. Evol. Comput..

[15]  G. F. D. A. Pereira Modelos de risco de crédito de clientes: Uma aplicação a dados reais , 2004 .

[16]  Sofie Balcaen,et al.  The Ooghe-Joos-De Vos failure prédiction models: a cross-industry validation , 2003 .

[17]  T. Harrison,et al.  Customer retention in the insurance industry: Using survival analysis to predict cross-selling opportunities , 2002 .

[18]  Kaisa Sere,et al.  Neural networks and genetic algorithms for bankruptcy predictions , 1996 .