AI Glossary

Recall@K

A retrieval metric measuring what fraction of relevant items appear in the top-K results returned by a search or recommendation system.

Formula

Recall@K = (relevant items in top K) / (total relevant items). For example, if there are 10 relevant documents and 7 appear in the top-20 results, Recall@20 = 0.7.

Usage

Standard metric for RAG systems, search engines, and recommendation systems. Often paired with precision@K and NDCG for a complete evaluation. Higher K means higher recall but potentially lower precision.

← Back to AI Glossary

Last updated: March 5, 2026