Description

Rank Score extends the recall metric to take the positions of correct items in a ranked list into account.

Usage

Arguments

Details

Rank Score is defined as the ratio of the Rank Score of the correct items to best theoretical Rank Score achievable for the user:

rankscore_{p} =∑_{i\in{h}} 2^{-\frac{rank(i)-1}{α}}

rankscore_{max} = ∑_{i=1}^{|T|} 2^{-\frac{i-1}{α}}

rankscore = \frac{rankscore_p}{rankscore_{max}}