recalculate_user for Bayesian Personalized Ranking

Open epetrovski opened this issue 6 years ago • 1 comments

Could the .recalculate_user() method be implemented for Bayesian Personalized Ranking?

I'm not sure if this is a lacking feature or if it's simply not theoretically possible with this algorithm - since it works for ALS. Currently the Bayesian Personalized Ranking class throws the following error when I try to call .recalculate_user():

NotImplementedError: recalculate_user is not supported with this model

Dec 05 '19 13:12 epetrovski

This would be nice!
Currently I figured out that for my dataset BPR performs much better than ALS.
I'm using NDCG@10 to evaluate.

Nov 27 '20 16:11 igorkf