Evaluation measures (information retrieval)

The evaluation measures of an information retrieval system is the process of assessing how well the search results satisfied the user's query intent. The metrics are often split in to multiple categories. Online metrics measure actual users' interactions with the search system. Offline metrics measure the relevance of the search engine by having expert judges measure how likely each result (or the SERP page as a whole) is to meet the information needs of the user. The mathematical symbols used in the formulas below mean: * - Cardinality - in this case, the number of documents in set X *

Evaluation measures (information retrieval)

The evaluation measures of an information retrieval system is the process of assessing how well the search results satisfied the user's query intent. The metrics are often split in to multiple categories. Online metrics measure actual users' interactions with the search system. Offline metrics measure the relevance of the search engine by having expert judges measure how likely each result (or the SERP page as a whole) is to meet the information needs of the user. The mathematical symbols used in the formulas below mean: * - Cardinality - in this case, the number of documents in set X *