Collaborative Filtering

Collaborative Filtering (CF) refers to a class of techniques used in recommender systems, that recommend items to users that other users with similar tastes have liked in the past. CF methods are commonly sub-divided into neighborhood-based and model-based approaches. In neighborhood-based approaches, a subset of users are chosen based on their similarity to the active user, and a weighted combination of their ratings is used to produce predictions for this user. In contrast, model-based approaches assume an underlying structure to users' rating behavior, and induce predictive models based on the past ratings of all users.