Command Palette
Search for a command to run...
Area Under the Receiver Operating Characteristic Curve AUROC
Date
Tags
Area Under the ROC Curve (AUROC / ROC-AUC) measures a classifier's overall ranking and discrimination ability in distinguishing positive and negative samples across different thresholds through the area under the curve of true positive rate versus false positive rate. Its value typically ranges from 0.5 to 1 (usually reported as a decimal or percentage; the higher the value, the better). It is one of the most commonly used comprehensive evaluation metrics in tasks such as binary classification, anomaly detection, OOD detection, medical diagnosis, and molecular property prediction (Note: in extreme class imbalance scenarios, it should be combined with PR-AUC for comprehensive evaluation).
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.