Average Precision at n
- Nick CraswellAffiliated withMicrosoft Research Cambridge
- , Stephen RobertsonAffiliated withMicrosoft Research Cambridge
Average Precision at n is a variant of Average Precision (AP) where only the top n ranked documents are considered (please see the entry on Average Precision for its definition). AP is already a top-heavy measure, but has a recall component because it is normalized according to R, the number of relevant documents for a query. In AP@n there are a number of options for normalization, for example, normalize by n or normalize by min(n,R).
The well-known measure Average Precision has a number of lesser-known variants, used in TREC  and elsewhere. Before and during TREC-1, it was usual to calculate an 11-point interpolated Precision-Recall curve, and take the average of these 11 precision values, giving an “interpolated AP.” In TREC-2 and beyond, the modern non-interpolated AP was introduced. It calculates precision at each relevant document.
A number of other AP variants arise in a precision-oriented setting, where it is possible ...
Reference Work Entry Metrics
- Average Precision at n
- Reference Work Title
- Encyclopedia of Database Systems
- pp 193-194
- Print ISBN
- Online ISBN
- Springer US
- Copyright Holder
- Springer Science+Business Media, LLC
- Additional Links
- Industry Sectors
- eBook Packages
- Editor Affiliations
- 1. College of Computing, Georgia Institute of Technology
- 2. Database Research Group David R. Cheriton School of Computer Science, University of Waterloo
- Author Affiliations
- 1. Microsoft Research Cambridge, Cambridge, UK
To view the rest of this content please follow the download PDF link above.