collaborative filtering

(redirected from Recommender system)
Also found in: Wikipedia.

collaborative filtering

Also known as "social filtering" and "social information filtering," it refers to techniques that identify information people might be interested in. Collaborative filtering is used to create "recommendation systems" that can enhance the experience on a website; for example, by suggesting music or movies.

Different algorithms are used, but the basic principle is to develop a rating system for matching incoming material. "Collaborative" means that a group of people interested in the subject define their preferences when setting up the system. See collaborative software and music recommendation service.
References in periodicals archive ?
Recommender system brings customer into contact with movies that he never seen.
ImpressTV Limited, a leading expert of real-time content recommendations on any device, has acquired the entertainment-based recommender system business line from Gravity R&D and dictates a rapid growth by welcoming Sentiance as a key partner for mobile.
The first chapter on recommendation process provides a focus on the fundamental concepts including the formal framework of recommender system, evaluation and challenges.
So the recommender system would suggest first those experts who had the closest social ties with the person asking.
There has been some work in the literature to increase the scalability by reducing the dimensions of the recommender system dataset using singular value decomposition (SVD); however, due to sparsity it results in inaccurate recommendations.
Last but not least, since 2009, SFX includes a recommender system, bX.
Typically, a recommender system compares the user's profile to some reference characteristics, and seeks to predict the 'rating' that a user would give to an item they had not yet considered.
A recommender system is a system that takes data about a user's past history in a certain industry, such as products they have purchased, movies they have seen, or websites they have visited, and predict what the user may prefer to purchase or see in the future.
Thereby a recommender system can be realised in the factory planning algorithm.
To take advantage of this information, CWIS includes a recommender system.
Making recommendations in e-learning is different from that in other domains (the most studied domain of recommender system is movie recommendations, (Basu, Hirsh, & Cohen, 1998; Herlocker, Konstan, Borchers, & Riedl, 1999; Schein, Popescul, Ungar, & Pennock, 2002; Melville, Mooney, & Nagarajan, 2002).
com uses a recommender system to recommend products to its users.