Average precision
Average precision is a ranking or classification metric that summarizes precision across the recall levels of a precision-recall curve.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
A classification metric that summarizes the precision-recall curve, typically by averaging precision over recall increments.
- How it is used
- Guides classifier evaluation when binary classes are imbalanced and predicted ordering is important.
- How deep it goes
- Defines the metric’s practical role but stops short of deriving or implementing the precision-recall calculation.
- Examples
- Uses an above-mean price target with 34,016 negative and 14,879 positive cases as the imbalanced classification example.
- What you can do after
- Evaluate imbalanced binary classifiers with a ranking-sensitive metric instead of relying only on accuracy.
AI Recommender Systems
Average precision is the mean of precision values at the ranked positions where relevant items occur for one user or query.
- How it is used
- Evaluates ranked recommendation lists by rewarding relevant items according to the positions where they appear.
- How deep it goes
- Defines AP precisely and situates its position-based calculation within a multi-metric evaluation loop, without detailing the full implementation.
- Examples
- Uses recommendation lists with binary consumed-item relevance and compares identical relevant items placed at different ranks.
- What you can do after
- Evaluate ranked recommendation outputs with a position-sensitive relevance metric alongside other top-K measures.
Read how AI Recommender Systems explains average precision →
What to know first
- precisionPrecision is the proportion of items predicted, selected, or retrieved as positive that are correct or relevant.
- recallRecall is the proportion of all relevant or actual positive items that a system successfully retrieves or correctly identifies.
Related concepts
- context precisionimplemented by · Context precision is a retrieval metric measuring how much retrieved context is relevant to answering a query and, in some formulations, how highly relevant items are ranked.
- mean average precisionpart of · Mean average precision is a metric that averages average-precision scores across queries, classes, or other evaluation units.
Questions about average precision
What is average precision?
Average precision is a ranking or classification metric that summarizes precision across the recall levels of a precision-recall curve.
Which Manning books explain average precision?
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI and AI Recommender Systems.
What should I know before learning average precision?
Manning books that teach average precision usually introduce precision and recall first.
What is average precision part of?
Average precision is part of mean average precision. Mean average precision is a metric that averages average-precision scores across queries, classes, or other evaluation units.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

