The Relationship Between Precision-Recall and ROC Curves
摘要：
Receiver Operator Characteristic (ROC) curves are commonly used to present results for binary decision problems in machine learning. However, when dealing with highly skewed datasets, Precision-Recall (PR) curves give a more informative picture of an algorithm's performance. We show that a deep connection exists between ROC space and PR space, such that a curve dominates in ROC space if and only if it dominates in PR space. A corollary is the notion of an achievable PR curve, which has properties much like the convex hull in ROC space; we show an efficient algorithm for computing this curve. Finally, we also note differences in the two types of curves are significant for algorithm design. For example, in PR space it is incorrect to linearly interpolate between points. Furthermore, algorithms that optimize the area under the ROC curve are not guaranteed to optimize the area under the PR curve.
展开
DOI：
10.1145/1143844.1143874
被引量：
年份：
2006
Semantic Scholar
掌桥科研
Semantic Scholar
(全网免费下载)
ResearchGate
(全网免费下载)
Citeseer
(全网免费下载)
查看更多
biostat.wisc.edu
(全网免费下载)
lirias.kuleuven.be
(全网免费下载)
research.cs.wisc.edu
(全网免费下载)
autonlab.org
(全网免费下载)
biostat.wisc.edu
(全网免费下载)
mark.goadrich.com
(全网免费下载)
pages.cs.wisc.edu
(全网免费下载)
citeseer.ist.psu.edu
(全网免费下载)
mark.goadrich.com
(全网免费下载)
ftp.cs.wisc.edu
(全网免费下载)
scienceopen.com
cs.wisc.edu
(全网免费下载)
minds.wisconsin.edu
(全网免费下载)
Semantic Scholar
(全网免费下载)
ResearchGate
(全网免费下载)
Citeseer
(全网免费下载)
lirias.kuleuven.be
(全网免费下载)
pages.cs.wisc.edu
(全网免费下载)
biostat.wisc.edu
(全网免费下载)
autonlab.org
(全网免费下载)
research.cs.wisc.edu
(全网免费下载)
biostat.wisc.edu
(全网免费下载)
mark.goadrich.com
(全网免费下载)
citeseer.ist.psu.edu
(全网免费下载)
ftp.cs.wisc.edu
(全网免费下载)
cs.wisc.edu
(全网免费下载)
mark.goadrich.com
(全网免费下载)
minds.wisconsin.edu
(全网免费下载)
通过文献互助平台发起求助，成功后即可免费获取论文全文。
相似文献
参考文献
引证文献
辅助模式
引用
文献可以批量引用啦~
欢迎点我试用！
