Unachievable Region in Precision-Recall Space and Its Effect on Empirical Evaluation
Machine Learning
2012-07-19 v2 Artificial Intelligence
Information Retrieval
Abstract
Precision-recall (PR) curves and the areas under them are widely used to summarize machine learning results, especially for data sets exhibiting class skew. They are often used analogously to ROC curves and the area under ROC curves. It is known that PR curves vary as class skew changes. What was not recognized before this paper is that there is a region of PR space that is completely unachievable, and the size of this region depends only on the skew. This paper precisely characterizes the size of that region and discusses its implications for empirical evaluation methodology in machine learning.
Keywords
Cite
@article{arxiv.1206.4667,
title = {Unachievable Region in Precision-Recall Space and Its Effect on Empirical Evaluation},
author = {Kendrick Boyd and Vitor Santos Costa and Jesse Davis and David Page},
journal= {arXiv preprint arXiv:1206.4667},
year = {2012}
}
Comments
ICML2012, fixed citations to use correct tech report number