📏  ROC-AUC (Receiver Operating Characteristic – Area Under Curve, = AUROC)

ROC-AUC (Receiver Operating Characteristic – Area Under Curve, = AUROC)#

The probability a random positive outranks a random negative.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

ROC-AUC is the area under the ROC curve, which plots the true positive rate (recall) against the false positive rate as the decision threshold sweeps from 0 to 1. It condenses that whole curve into one number in \([0, 1]\).

How to read it#

1.0 is a perfect classifier, 0.5 is random guessing. It has a clean probabilistic meaning — the chance that a randomly chosen positive is scored higher than a randomly chosen negative — so it measures ranking quality, independent of any single threshold and invariant to the score scale.

The caveat#

Because the false positive rate has all the true negatives in its denominator, ROC-AUC can look optimistically high on imbalanced data where negatives dominate — a model can score well while still flooding a rare positive class with false alarms. There, PR-AUC is more honest.


Theme: Classification & Averaging Metrics  ·  All terminology



See also

Source article Adapted (context, re-expressed) in our own words from: ROC-AUC (Receiver Operating Characteristic – Area Under Curve, = AUROC) (insightful-data-lab.com).

Tags: purpose: reference topic: terminology level: intermediate