Abstract
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\nan 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\nin 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.
Keywords
Receiver operating characteristicSpace (punctuation)MathematicsConvex hullAlgorithmPrecision and recallBinary numberComputer scienceConnection (principal bundle)Artificial intelligenceRegular polygonStatisticsGeometryArithmetic
Affiliated Institutions
Related Publications
An Evaluation of Methods for Estimating the Area Under the Receiver Operating Characteristic (ROC) Curve
The area under the receiver operating characteristic (ROC) curve serves as one means for evaluating the performance of diagnostic and predictive test systems. The most commonly ...
A Computer Program for Rapid Generation of Receiver Operating Characteristic Curves and Likelihood Ratios in the Evaluation of Diagnostic Tests
We describe a MUMPS program to facilitate the evaluation of the diagnostic effectiveness and efficiency of laboratory tests using receiver operating characteristic (ROC) curves ...
Receiver operating characteristic curve: overview and practical use for clinicians
Using diagnostic testing to determine the presence or absence of a disease is essential in clinical practice. In many cases, test results are obtained as continuous values and r...
A method of comparing the areas under receiver operating characteristic curves derived from the same cases.
Receiver operating characteristic (ROC) curves are used to describe and compare the performance of diagnostic technology and diagnostic algorithms. This paper refines the statis...
Classification assessment methods
Classification techniques have been applied to many applications in various fields of sciences. There are several ways of evaluating classification algorithms. The analysis of s...
Publication Info
- Year
- 2006
- Type
- article
- Pages
- 233-240
- Citations
- 5914
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
5914
OpenAlex
Cite This
Jesse Davis,
Mark Goadrich
(2006).
The relationship between Precision-Recall and ROC curves.
, 233-240.
https://doi.org/10.1145/1143844.1143874
Identifiers
- DOI
- 10.1145/1143844.1143874