Precision and Recall Reject Curves for Classification

TL;DR

This paper introduces reject curves based on precision and recall to evaluate classifier performance in high-certainty scenarios, especially for imbalanced data, providing more relevant insights than traditional accuracy-based reject curves.

Contribution

The paper proposes new reject curves for precision and recall, extending existing accuracy reject curves to better suit applications with imbalanced data and different performance metrics.

Findings

Precision- and recall-reject curves outperform accuracy reject curves on imbalanced and real-world data.

Prototype-based classifiers validate the effectiveness of the proposed curves.

The new curves offer more relevant insights into classifier performance in specific scenarios.

Abstract

For some classification scenarios, it is desirable to use only those classification instances that a trained model associates with a high certainty. To obtain such high-certainty instances, previous work has proposed accuracy-reject curves. Reject curves allow to evaluate and compare the performance of different certainty measures over a range of thresholds for accepting or rejecting classifications. However, the accuracy may not be the most suited evaluation metric for all applications, and instead precision or recall may be preferable. This is the case, for example, for data with imbalanced class distributions. We therefore propose reject curves that evaluate precision and recall, the recall-reject curve and the precision-reject curve. Using prototype-based classifiers from learning vector quantization, we first validate the proposed curves on artificial benchmark data against the accuracy reject curve as a baseline. We then show on imbalanced benchmarks and medical, real-world data that for these scenarios, the proposed precision- and recall-curves yield more accurate insights into classifier performance than accuracy reject curves.