This paper investigates the performance of two-class classification credit scoring data sets with low default ratios. The standard two-class parametric Gaussian and non-parametric Parzen classifiers are extended, using Bayes’ rule, to include either a class imbalance or a Bernoulli prior. This is done with the aim of addressing the low default probability problem. Furthermore, the performance of Parzen classification with Silverman and Minimum Leave-one-out Entropy (MLE) Gaussian kernel bandwidth estimation is also investigated.
Reference:
Rademeyer, E., Van der Walt, C.M. and De Waal, A. 2016. Low default credit scoring using two-class non-parametric kernel density estimation. Proceedings of the Twenty-Seventh Annual Symposium of the Pattern Recognition Association of South Africa, 30 November - 2 December 2016, Stellenbosch, South Africa. DOI: 10.1109/RoboMech.2016.7813152
Rademeyer, E., Van der Walt, C. M., & De Waal, A. (2016). Low default credit scoring using two-class non-parametric kernel density estimation. IEEE. http://hdl.handle.net/10204/9369
Rademeyer, E, Christiaan M Van der Walt, and A De Waal. "Low default credit scoring using two-class non-parametric kernel density estimation." (2016): http://hdl.handle.net/10204/9369
Rademeyer E, Van der Walt CM, De Waal A, Low default credit scoring using two-class non-parametric kernel density estimation; IEEE; 2016. http://hdl.handle.net/10204/9369 .
Copyright: 2016 IEEE. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, kindly consult the publisher's website.
ResearchSpace
