What is the evaluation measure expected reciprocal rank (ERR)?

Information Retrieval Questions



44 Short 80 Medium 48 Long Answer Questions Question Index

What is the evaluation measure expected reciprocal rank (ERR)?

The evaluation measure expected reciprocal rank (ERR) is a metric used in information retrieval to assess the effectiveness of a ranking algorithm. It calculates the average reciprocal rank of the documents in a ranked list based on their relevance to a given query. ERR takes into account both the position of the relevant documents in the list and their graded relevance, providing a more comprehensive evaluation of the ranking quality compared to other measures like precision or recall.