Abstract
With increasing amounts of information available, modeling and predicting user preferences—for books or articles, for example—are becoming more important. We present a collaborative filtering model, with an associated scalable algorithm, that makes accurate predictions of users’ ratings. Like previous approaches, we assume that there are groups of users and of items and that the rating a user gives an item is determined by their respective group memberships. However, we allow each user and each item to belong simultaneously to mixtures of different groups and, unlike many popular approaches such as matrix factorization, we do not assume that users in each group prefer a single group of items. In particular, we do not assume that ratings depend linearly on a measure of similarity, but allow probability distributions of ratings to depend freely on the user’s and item’s groups. The resulting overlapping groups and predicted ratings can be inferred with an expectation-maximization algorithm whose running time scales linearly with the number of observed ratings. Our approach enables us to predict user preferences in large datasets and is considerably more accurate than the current algorithms for such large datasets.
Funder
John Templeton Foundation
James S. McDonnell Foundation
DOD | Army Research Office
Ministerio de Economía y Competitividad
Seventh Framework Programme
Publisher
Proceedings of the National Academy of Sciences
Reference30 articles.
1. A survey of collaborative filtering techniques;Su;Adv Artif Intell,2009
2. Predicting Human Preferences Using the Block Structure of Complex Social Networks
3. Mixed membership stochastic blockmodels;Airoldi;J Mach Learn Res,2008
4. Model selection and hypothesis testing for large-scale network models with overlapping groups;Peixoto;Phys Rev X,2015
5. Probabilistic forecasts, calibration and sharpness;Gneiting;J R Stat Soc B,2007
Cited by
37 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献