Skip to content
AI’s

evaluation

AUC-ROC

Area Under the Receiver Operating Characteristic Curve, a metric that measures a classifier's ability to distinguish between classes across all classification thresholds. AUC-ROC ranges from 0.5 (random) to 1.0 (perfect separation).

In practice

An AUC-ROC of 0.95 means the model correctly ranks a random positive example above a random negative example 95% of the time.