I just wanted to know if receiving an overall MAP score of 0 in a recommendation engine was possible, or a sign that my calculation or my logic for the engine was wrong.
$\begingroup$
$\endgroup$
2
-
$\begingroup$ what's the number of the possible labels and also the population of your data? $\endgroup$– Alireza ZolanvariCommented Apr 30, 2019 at 6:03
-
$\begingroup$ @AlirezaZolanvari my data is the movie lens dataset the labels would be the rating. So I’m comparing the predicted rating (via an ALS model) and the actual rating (which ranges from 0-5) $\endgroup$– gbdataCommented Apr 30, 2019 at 16:27
Add a comment
|