Social filtering, or collaborative filtering, filters information by using the recommendations of other people. The principle behind collaborative filtering is that the customers who have appreciated the same items in the past have a high probability of displaying similar interests in the future as well.

We generally ask for reviews and recommendation from friends prior to watching a movie. A recommendation from a friend is more accepted than recommendations from others as we share some interests with our friends. This is the same principle on which collaborative filtering works.

Collaborative filtering can be further classified into memory-based and model-based as follows:

• Memory-based: In this method, user rating information is used to compute the likeness between users or items. This computed likeness is then used to come up with recommendations.
• Model based: Data mining methods are applied to recognize patterns in the data, and the learned patterns are then used to generate recommendations.