The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets¶
Saito, T., & Rehmsmeier, M. (2015). The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLOS ONE, 10(3).
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Classification Confusion or Error Matrix
- Its central failure mode is class imbalance: when one class dominates the sample, a matrix (and any accuracy read off it) can look excellent while a rare-but-important class is almost entirely confused away, its errors lost in a giant diagonal cell next door.
This sourceShows that class imbalance can conceal poor minority-class performance behind strong aggregate results.
- Its central failure mode is class imbalance: when one class dominates the sample, a matrix (and any accuracy read off it) can look excellent while a rare-but-important class is almost entirely confused away, its errors lost in a giant diagonal cell next door.
- ROC or Precision–Recall Surface Review
- Its failure mode is summary blindness: a single headline AUC averages over threshold regions you will never operate in, and under heavy class imbalance a great-looking ROC can hide a terrible precision-recall reality because the metric ignores the base rate.
This sourceShows that ROC plots can appear overly optimistic on highly imbalanced data and that precision-recall plots more informatively expose classifier performance in that setting.
- Its failure mode is summary blindness: a single headline AUC averages over threshold regions you will never operate in, and under heavy class imbalance a great-looking ROC can hide a terrible precision-recall reality because the metric ignores the base rate.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. Neither this nor any other of the 2 citations of this work carries a recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:806684b7b552 · see in the full table