A Hybrid Model of AdaBoost and Back-Propagation Neural Network for Credit Scoring
Owing to the development of internet finance in China, credit scoring is growing into one of the most important issues in the field of financial risk management. Quantitative credit scoring models are widely used tools for credit risk assessment in financial institutions. In this study, an AdaBoost algorithm model based on back-propagation neural network for credit scoring with high accuracy and efficiency is proposed. We first illustrate the basic concepts of back-propagation neural network and AdaBoost algorithm and propose a hybrid model of AdaBoost and back-propagation neural network, then two real-world credit data sets are selected to demonstrate the effectiveness and feasibility of the proposed model. The results show that the proposed model can get higher accuracy compared to other classifiers listed in this study.
KeywordsCredit scoring AdaBoost model Back-propagation neural network
This research was supported by the project of Research Center for System Sciences and Enterprise Development (Grant No.Xq16C03).
- 6.Chen M, Ma L, Gao Y (2010) Vehicle detection segmentation based on adaboost and grabcut. In: IEEE International Conference on Progress in Informatics and Computing, pp 896–900Google Scholar
- 9.Essa EM, Tolba AS, Elmougy S (2008) A comparison of combined classifier architectures for arabic speech recognition. In: International Conference on Computer Engineering & Systems, pp 149–153Google Scholar
- 10.Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: European Conference on Computational Learning Theory, pp 119–139Google Scholar
- 11.Gestel TV, Baesens B et al (2003) A support vector machine approach to credit scoring. Banken Financiewezen 2:73–82Google Scholar
- 12.Henley WE, Hand DJ (1996) A k-nearest-neighbour classifier for assessing consumer credit risk. J Roy Stat Soc 45(1):77–95Google Scholar
- 21.Malhotra R, Malhotra DK (2003) Evaluating consumer loans using neural networks. Soc Sci Electron Publishing 31(2):83–96Google Scholar
- 28.Varetto F (1951) Genetic algorithms in the analysis of insolvency risk. University of Illinois Press, ChampaignGoogle Scholar