RECOMMENDER SYSTEMS AND METHODS

A method for providing personalized item recommendations in a communication system comprising a server and a plurality of client devices is disclosed. The method comprises the steps of: at the server, receiving (S100) a plurality of user rating vectors r u from a plurality of said client devices; at the server, aggregating (S100) the user rating vectors r u into a rating matrix R; at the server, factorizing (S120) said rating matrix R into a user feature matrix P and an item feature matrix Q, wherein the product R of said user feature matrix P and said item feature matrix Q approximates the user rating matrix R, said factorization comprising the steps of transmitting (S130), from the server, said item feature matrix Q to at least one client device; generating (S140) a predictive rating vector r u as the product of the associated user feature vector p u and the item feature matrix Q; and by using a predefined selection scheme, selecting (S150) at least one item for recommendation to user from the items associated with the predictive rating vector r u . A server, a system and a computer program product for implementing the method are also disclosed.