A Support Vector Machine Based Method for Credit Risk Assessment

The credit card industry has been growing rapidly in recent years, and credit risk assessment becomes critically important for financial companies. In this paper, a novel support vector machine (SVM) based ensemble model is proposed for credit risk assessment. In the proposed method, principles component analysis (PCA) is firstly employed for credit feature selection. Secondly, SVMs with different kernels are trained by using genetic algorithm (GA) to optimize the parameters, and the corresponding assessment results are obtained. Thirdly, all results produced by different SVMs are combined by several ensemble strategies. Finally, an optimal ensemble strategy is selected for credit scoring. For validation, two real world credit datasets are used to test the effectiveness and efficiency of our proposed method. The experiment results find that our proposed ensemble model outperforms commonly used credit scoring tools. The findings of the study reveal the support vector machine based ensemble method to be a promising alternative for credit scoring.

[1]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[2]  Shu-Heng Chen,et al.  Computationally intelligent agents in economics and finance , 2007, Inf. Sci..

[3]  Alexander Gammerman,et al.  Machine-learning algorithms for credit-card applications , 1992 .

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

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

[6]  Kemal Polat,et al.  Principles component analysis, fuzzy weighting pre-processing and artificial immune recognition system based diagnostic system for diagnosis of lung cancer , 2008, Expert Syst. Appl..

[7]  Minghui Jiang,et al.  Construction and Application of PSO-SVM Model for Personal Credit Scoring , 2007, International Conference on Computational Science.

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Jianchang Mao,et al.  A case study on bagging, boosting and basic ensembles of neural networks for OCR , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[10]  Bart Baesens,et al.  COMPARING A GENETIC FUZZY AND A NEUROFUZZY CLASSIFIER FOR CREDIT SCORING , 2002 .

[11]  Kin Keung Lai,et al.  Least squares support vector machines ensemble models for credit scoring , 2010, Expert Syst. Appl..

[12]  Lun-Ping Hung,et al.  A data driven ensemble classifier for credit scoring analysis , 2010, Expert Syst. Appl..

[13]  Bernhard Schölkopf,et al.  Statistical Learning and Kernel Methods , 2001, Data Fusion and Perception.

[14]  Lin Ma,et al.  Mining the customer credit using hybrid support vector machine technique , 2009, Expert Syst. Appl..

[15]  Tian-Shyug Lee,et al.  A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines , 2005, Expert Syst. Appl..

[16]  William Edward Henley,et al.  Statistical aspects of credit scoring , 1995 .

[17]  Bhekisipho Twala,et al.  Multiple classifier application to credit risk assessment , 2010, Expert Syst. Appl..

[18]  Wuyi Yue,et al.  Support vector machine based multiagent ensemble learning for credit risk evaluation , 2010, Expert Syst. Appl..

[19]  C ONG,et al.  Building credit scoring models using genetic programming , 2005, Expert Syst. Appl..

[20]  Yingxu Yang,et al.  Adaptive credit scoring with kernel learning methods , 2007, Eur. J. Oper. Res..

[21]  Alan K. Reichert,et al.  An Examination of the Conceptual Issues Involved in Developing Credit-Scoring Models , 1983 .

[22]  Bernhard Schölkopf,et al.  Support Vector Machines , 2005 .

[23]  Rashmi Malhotra,et al.  Differentiating between Good Credits and Bad Credits Using Neuro-Fuzzy Systems , 2001, Eur. J. Oper. Res..

[24]  Guido Dedene,et al.  A case study of applying boosting naive Bayes to claim fraud diagnosis , 2004, IEEE Transactions on Knowledge and Data Engineering.

[25]  Nan-Chen Hsieh,et al.  Hybrid mining approach in the design of credit scoring models , 2005, Expert Syst. Appl..

[26]  Kin Keung Lai,et al.  Credit risk assessment with a multistage neural network ensemble learning approach , 2008, Expert Syst. Appl..

[27]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

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

[29]  Luc Vandendorpe,et al.  Multiple classifier combination for face-based identity verification , 2004, Pattern Recognit..