True positive rate is a classification metric measuring the proportion of actual positive cases that a model correctly identifies, also known as sensitivity or recall.
Semantic Classification
Content
- True positive rate is computed as the number of true positives divided by the sum of true positives and false negatives. It quantifies how well a classifier detects positive cases and is equivalent to recall and sensitivity.
- It is one axis of the receiver operating characteristic curve, plotted against the false positive rate, and is read from the confusion matrix that tabulates predicted against actual class labels.