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

Precision-Recall-Gain curves: PR analysis done right

Peter Flach; Kull, M.;
Open Access
  • Published: 12 Dec 2015
  • Country: United Kingdom
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...
Read more
handle: 1983/254121da-3dac-4b70-8168-920ca7dccce3
Subjects
free text keywords: /dk/atira/pure/core/keywords/jean_golding, Jean Golding
Related Organizations
Download fromView all 2 versions
Explore Bristol Research
Contribution for newspaper or weekly magazine . 2015
Provider: Explore Bristol Research
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue