Working Paper: When to Consult Precision-Recall Curves

Paper Authors: Jonathan A. Cook and Vikram Ramadas​

Abstract:  OC curves are commonly used to evaluate predictions of binary outcomes. When there are a small percentage of items of interest (as would be the case with fraud detection, for example), ROC curves can provide an inflated view of performance. This can cause challenges in trying to distinguish between two sets of predictions. This article discusses the conditions under which precision-recall curves may be preferable to ROC curves. As an illustrative example, we compare two commonly used fraud predictors (Beneish's (1999) M-score and Dechow et al.'s (2011) F-score) using both ROC and precision-recall curves.