On the application of ROC analysis to predict classification performance under varying class distributions

Abstract

We counsel caution in the application of ROC analysis for prediction of classifier performance under varying class distributions. We argue that it is not reasonable to expect ROC analysis to provide accurate prediction of model performance under varying distributions if the classes contain causally relevant subclasses whose frequencies may vary at different rates or if there are attributes upon which the classes are causally dependent. 2005 Springer Science + Business Media, Inc.