Similarity measure

From RecSysWiki
Jump to navigation Jump to search

A similarity measure is a metric that, given two objects (e.g. two 2-dimensional points, or two time-series), calculates their similarity in terms of inverted distance in the range [0,1]. The larger the value of the similarity measure is, the more similar the two objects are. Examples of known similarity measures are cosine similarity and the Jaccard coefficient.