Glossary term
Glossary term
Evaluation and Benchmarks
A metric for evaluating systems that output a ranked (ordered) list of items. Recall at k identifies the fraction of relevant items in the first k items in that list out of the total number of relevant items returned.
Contrast with precision at k.
Click the icon to see an example.
Created for this library
A search team uses recall at 100 to measure how many relevant documents are captured in the top 100 retrieved before re-ranking.
A retail recommender team uses recall at 20 to evaluate how much relevant inventory the candidate generator surfaces.
A help-center search team uses recall at 5 to ensure the most relevant articles are within the first five results.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License