Average Precision: average of the precision at each recall level.
Average of a recommendation metric: system metric based on the arithmetic mean of a recommendation metric for a set of users' recommendations.
Normalized Discounted Cumulative Gain metric.
Relevance model for nDCG, in which the gains of all relevant documents need to be known for the normalization of the metric.
Number of recommended items.
Precision metric: proportion of relevant items in a recommendation list.
Recall metric: proportion of relevant items in a recommendation list to all relevant items.
Reciprocal Rank (RR, also known as MRR when averaged over queries/users).
Recommendability: binary metric that determines whether the user receives a non-empty recommendation or not.
Copyright © 2016. All rights reserved.