Glossary term
Glossary term
Evaluation and Benchmarks
A metric for evaluating a ranked (ordered) list of items. Precision at k identifies the fraction of the first k items in that list that are "relevant." That is:
The value of k must be less than or equal to the length of the returned list. Note that the length of the returned list is not part of the calculation.
Relevance is often subjective; even expert human evaluators often disagree on which items are relevant.
Compare with:
Click the icon to see an example.
Created for this library
A search-quality team uses precision at 10 because the top of the result page is what shoppers actually engage with.
A help-center search team uses precision at 5 because users rarely click past the first five results.
A retention team uses precision at top-k where k matches the number of customers the call center can reach in a day.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License