A geometric interpretation and analysis of R-precision
Javed A. Aslam, Emine Yılmaz · 2005
Average precision and R-precision are two of the most commonly cited measures of overall retrieval performance, but their correlation, though well-known, has defied explanation. We recently devised a geometric interpretation of R-precision which suggests that under a reasonable set of assumptions, R-precision approximates the area under the precision-recall curve, as does average precision, thus explaining their correlation. In this paper, we consider these assumptions and our geometric interpretation of R-precision in order to further understand, and make reasonable use of, the information that R-precision provides. Given our geometric interpretation of R-precision, we show that R-precision is highly informative by demonstrating that it can be used to (1) accurately infer precision-recall curves, (2) accurately infer other measures of retrieval performance, and (3) devise new measures of retrieval performance. Through our analysis, we also state the conditions under which R-precision is informative.