Credit Scoring Using PCA-SVM Hybrid Model
A new approach for credit scoring using principal component analysis (PCA) and support vector machine (SVM) in tandem is proposed in this paper. The proposed credit scoring hybrid algorithm consists of two basic steps. In the first step, PCA is employed for dimension reduction and in the second, SVM is employed for classification purpose, resulting in PCA-SVM hybrid model. The effectiveness of PCA-SVM model is evaluated using German and UK credit data sets. It is observed that PCA-SVM outperforms stand-alone SVM and PCA-Logistic Regression (LR) hybrid. However, in terms of sensitivity alone, LR outperformed PCA-SVM hybrid.
KeywordsCredit Scoring SVM PCA Logistic Regression dimension reduction
Unable to display preview. Download preview PDF.
- 1.Durand, D.: Risk Elements in Consumer Installment Financing. National Bureau of Economic Research (1941)Google Scholar
- 3.Henley, W.E.: Statistical aspects of credit scoring. Dissertation, The Open University, Milton Keynes, UK (1995)Google Scholar
- 8.Wang, Y., Wang, S., Lai, K.K.: A New Fuzzy Support Vector Machine to Evaluate Credit Risk. IEEE Transactions on Fuzzy Systems 13(6) (2005)Google Scholar
- 9.Setiono, R., Baesens, B., Mues, M.: Recursive Neural Network Rule Extraction for Data with Mixed Attributes. IEEE Transactions on Neural Networks 19(2) (2008)Google Scholar
- 10.Zhang, D., Hifi, M., Chen, Q., Ye, W.: A Hybrid Credit Scoring Model Based on Genetic Programming and Support Vector Machines. In: Fourth International Conference on Natural Computation, pp. 8–12 (2008)Google Scholar
- 11.Jiang, Y.: Credit Scoring Model Based on the Decision Tree and the Simulated Annealing Algorithm. In: World Congress on Computer Science and Information Engineering, pp. 18–21 (2009)Google Scholar
- 12.Zhang, L.-L., Hui, X.-F., Wang, L.: Application of Adaptive Support Vector Machines Method in Credit Scoring. In: 16th International Conference on Management Science & Engineering, Moscow, Russia, September 14-16, pp. 1411–1415 (2009)Google Scholar
- 13.Yao, P.: Hybrid Classifier Using Neighborhood Rough Set and SVM for Credit Scoring. In: International Conference on Business Intelligence and Financial Engineering, pp. 138–142 (2009)Google Scholar
- 14.Qin, R., Liu, L.L., Xie, J.: An Application of Improved BP Neural Network in Personal Credit Scoring. In: Second International Conference on Computer Modeling and Simulation, pp. 238–241 (2010)Google Scholar
- 17.Strauss, D.: The many faces of Logistic Regression. The American statistician 46(4), 321–326 (1992)Google Scholar