Abstract
In practical applications to credit risk evaluation, most prediction models often make inaccurate decisions because of the lack of sufficient default data. The challenging issue of highly skewed class distribution between defaulter and non-defaulters is here faced by means of an algorithmic solution based on cost-sensitive learning. The present study is conducted on the popular Multilayer Perceptron neural network using three misclassification cost functions, which are incorporated into the training process. The experimental results on real-life credit data sets show that the proposed cost functions to train such a neural network are quite effective to improve the prediction of examples belonging to the defaulter (minority) class.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alfaro-Cid, E., Sharman, K.C., Esparcia-Alcázar, A.I.: A genetic programming approach for bankruptcy prediction using a highly unbalanced database. In: Giacobini, M. (ed.) EvoWorkshops 2007. LNCS, vol. 4448, pp. 169–178. Springer, Heidelberg (2007)
Brown, I., Mues, C.: An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Systems with Applications 39(3), 3446–3453 (2012)
Crone, S.F., Finlay, S.: Instance sampling in credit scoring: An empirical study of sample size and balancing. International Journal of Forecasting 28(1), 224–238 (2003)
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research 7(1), 1–30 (2006)
Finlay, S.: Multiple classifier architectures and their application to credit risk assessment. European Journal of Operational Research 210, 368–378 (2011)
Frank, A., Asuncion, A.: UCI machine learning repository (2010), http://archive.ics.uci.edu/ml
García, S., Fernández, A., Luengo, J., Herrera, F.: Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power. Information Sciences 180(10), 2044–2064 (2010)
Hand, D.J., Vinciotti, V.: Choosing k for two-class nearest neighbour classifiers with unbalanced classes. Pattern Recognition Letters 24(9-10), 1555–1562 (2003)
Harris, T., Gittens, C.: Minimising expected misclassification cost when using support vector machines for credit scoring. In: Proc. 7th International Multi-Conference on Computing in the Global Information Technology, pp. 225–231 (2012)
Kennedy, K., Mac Namee, B., Delany, S.J.: Learning without default: A study of one-class classification and the low-default portfolio problem. In: Coyle, L., Freyne, J. (eds.) AICS 2009. LNCS, vol. 6206, pp. 174–187. Springer, Heidelberg (2010)
Marqués, A.I., García, V., Sánchez, J.S.: On the suitability of resampling techniques for the class imbalance problem in credit scoring. Journal of the Operational Research Society (2012), doi:10.1057/jors.2012.120
Paleologo, G., Elisseeff, A., Antonini, G.: Subagging for credit scoring models. European Journal of Operational Research 201, 490–499 (2010)
Sabzevari, H., Soleymani, M., Noorbakhsh, E.: A comparison between statistical and data mining methods for credit scoring in case of limited available data. In: Proc. the 3rd CRC Credit Scoring Conference (2007)
Schebesch, K.B., Stecking, R.: Support vector machines for credit scoring: extension to non standard cases. In: Proc. of the 27th Annual Conference of the Gesellschaft fur Klassikation e. V., pp. 443–451 (2003)
Stecking, R., Schebesch, K.B.: Classification of large imbalanced credit client data with cluster based SVM. In: Proc. of the 34th Annual Conference of the Gesellschaft fur Klassikation e. V., pp. 443–451 (2008)
Thai-Nghe, N., Nghi, D.T., Schmidt-Thieme, L.: Learning optimal threshold on resampling data to deal with class imbalance. In: Proc. IEEE RIVF International Conference on Computing and Telecommunication Technologies, pp. 71–76 (2010)
Thomas, L.C., Edelman, D.B., Crook, J.N.: Credit Scoring and Its Applications. SIAM, Philadelphia (2002)
Vinciotti, V., Hand, D.J.: Scorecard construction with unbalanced class sizes. Journal of the Iranian Statistical Society 2(2), 189–205 (2003)
Yao, P.: Comparative study on class imbalance learning for credit scoring. In: Proc. 9th International Conference on Hybrid Intelligent Systems, vol. 2, pp. 105–107 (2009)
Zhang, L., Wang, W.: A re-sampling method for class imbalance learning with credit data. In: Proc. the 2011 International Conference on Information Technology, Computer Engineering and Management Sciences, pp. 393–397 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Alejo, R., García, V., Marqués, A.I., Sánchez, J.S., Antonio-Velázquez, J.A. (2013). Making Accurate Credit Risk Predictions with Cost-Sensitive MLP Neural Networks. In: Casillas, J., Martínez-López, F., Vicari, R., De la Prieta, F. (eds) Management Intelligent Systems. Advances in Intelligent Systems and Computing, vol 220. Springer, Heidelberg. https://doi.org/10.1007/978-3-319-00569-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-00569-0_1
Publisher Name: Springer, Heidelberg
Print ISBN: 978-3-319-00568-3
Online ISBN: 978-3-319-00569-0
eBook Packages: EngineeringEngineering (R0)