publication . Conference object . Contribution for newspaper or weekly magazine . 2015

Precision-Recall-Gain curves: PR analysis done right

Name: Precision-Recall-Gain curves: PR analysis done right
Keywords: /dk/atira/pure/core/keywords/jean_golding, Jean Golding

Peter Flach; Kull, M.;

Published: 01 Dec 2015

Country: United Kingdom

Summary

Abstract

Precision-Recall analysis abounds in applications of binary classification where true negatives do not add value and hence should not affect assessment of the classifier's performance. Perhaps inspired by the many advantages of receiver operating characteristic (ROC) curves and the area under such curves for accuracy-based performance assessment, many researchers have taken to report Precision-Recall (PR) curves and associated areas as performance metric. We demonstrate in this paper that this practice is fraught with difficulties, mainly because of incoherent scale assumptions -- e.g., the area under a PR curve takes the arithmetic mean of precision values wher...

Subjects

free text keywords: /dk/atira/pure/core/keywords/jean_golding, Jean Golding

Related Organizations

University of Bristol
United Kingdom

Download fromView all 3 versions

Explore Bristol Research

Contribution for newspaper or weekly magazine . 2015

Provider: Explore Bristol Research

Any information missing or wrong?Report an Issue