Precision and Recall

Precision and recall are fundamental measures of relevance in information retrieval. Precision is the number of relevant documents retrieved divided by the total number retrieved. Recall is the number of relevant documents retrieved divided by the total number of relevant documents in the collection.

For example, if a collection has 100 relevant documents and a system retrieves 50 documents, 30 of which are relevant, precision is 30/50 = 0.6 and recall is 30/100 = 0.3. These metrics were standardized by the TREC conference in the 1990s.