Working Papers Series 2010, 1 : [1] Collection home page

Giovanna Menardi, Nicola Torelli
Effect of training set selection when predicting defaulter SMEs with unbalanced data

Browse
Collection's Items (Sorted by Submit Date in Descending order): 1 to 1 of 1
PreviewIssue DateTitleAuthor(s)
DEAMS_wp1_2010.pdf.jpg12-Jan-2011Effect of training set selection when predicting defaulter SMEs with unbalanced dataMenardi, Giovanna; Torelli, Nicola
Collection's Items (Sorted by Submit Date in Descending order): 1 to 1 of 1
Subscribe to this collection to receive daily e-mail notification of new additions RSS Feed RSS Feed RSS Feed

We focus on credit scoring methods to separate defaulter small and medium enterprises from non-defaulter ones. In this framework, a typical problem occurs because the proportion of defaulter firms is very close to zero, leading to a class imbalance problem. Moreover, a form of bias may aect the classication. In fact, classication models are usually based on balance sheet items of large corporations which are not randomly selected. We investigate how dierent criteria of sample selection may aect the accuracy of the classication and how this problem is strongly related to the imbalance of the classes.