AI engineering glossary · Evaluation metrics
What is AP (average precision)?
Average precision (also called AP, AUC-PR): A single number that summarises the precision-recall curve, computed as the weighted mean of the precision achieved at each threshold, with the weights being the increase in recall. Higher is better, and it is preferred to ROC AUC when the positive class is rare.
Average precision: an example
A rare-defect detector scoring average precision 0.72 on a test set is doing much better than one at 0.30, even if both have ROC AUC above 0.9.
Related terms
More Evaluation metrics terms
- Balanced accuracy
- BERTScore
- Bits per byte
- BLEU
- Brier score
- Calibration
- Calinski-Harabasz index
- Catalogue coverage
Where you learn it
Average precision is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.