Update README.md

README.md

@@ -4,7 +4,7 @@ Bayesian Personalized Ranking (BPR) [1] is a recommender systems algorithm that
 
 This implementation uses the MovieLens data set [2] but the implementation can be used for any recomender system application.
 
-BPR learns latent factors of a user and an item (movie) and based on inner products of user and item embeddings, it ranks movies in the decreasing order of the predicted rating. The algorithm can be used for any application where implicit or explicit preferences of guests are available.
+BPR learns latent factors of a user and an item (movie) and based on inner products of user and item embeddings, it ranks movies in the decreasing order of the predicted rating. The algorithm can be used for any application where implicit or explicit preferences of guests are available. The algorithm is similar to collaborative filtering algorithms, and can be used for matrix factorization/completion problems.
 
 BPR puts a zero mean Gaussian prior on the learnt latent factors (embeddings) which results in an L2 regularization term in the loss function (the algorithm performs pretty well even without this extra term).