Google News Personalization: Scalable Online Collaborative Filtering

@inproceedings{citeulike:2719467, abstract = {Several approaches to collaborative filtering have been studied but seldom have the studies been reported for large (several millions of users and items) and dynamic (the underlying item set is continually changing) settings. In this paper we describe our approach to collaborative filtering for generating personalized recommendations for users of Google News. We generate recommendations using three approaches: collaborative filtering using MinHash clustering, Probabilistic Latent Semantic Indexing (PLSI), and covisitation counts. We combine recommendations from different algorithms using a linear model. Our approach is content agnostic and consequently domain independent, making it easily adaptible for other applications and languages with minimal effort. This paper will describe our algorithms and system setup in detail, and report results of running the recommendations engine on Google News.}, author = {Das, Abhinandan and Datar, Mayur and Garg, Ashutosh and Rajaram, Shyam }, booktitle = {16th International World Wide Web Conference}, citeulike-article-id = {2719467}, keywords = {collaborative-filtering, filtering, google, machine-learning, mapreduce, recommendation}, month = {May}, posted-at = {2008-04-25 22:00:38}, priority = {2}, title = {Google News Personalization: Scalable Online Collaborative Filtering}, url = {http://www2007.org/paper570.php}, year = {2007} }

TY - CONF ID - citeulike:2719467 TI - Google News Personalization: Scalable Online Collaborative Filtering T2 - 16th International World Wide Web Conference N2 - Several approaches to collaborative filtering have been studied but seldom have the studies been reported for large (several millions of users and items) and dynamic (the underlying item set is continually changing) settings. In this paper we describe our approach to collaborative filtering for generating personalized recommendations for users of Google News. We generate recommendations using three approaches: collaborative filtering using MinHash clustering, Probabilistic Latent Semantic Indexing (PLSI), and covisitation counts. We combine recommendations from different algorithms using a linear model. Our approach is content agnostic and consequently domain independent, making it easily adaptible for other applications and languages with minimal effort. This paper will describe our algorithms and system setup in detail, and report results of running the recommendations engine on Google News. KW - collaborative-filtering KW - filtering KW - google KW - machine-learning KW - mapreduce KW - recommendation AU - Das, Abhinandan AU - Datar, Mayur AU - Garg, Ashutosh AU - Rajaram, Shyam PY - 2007/05/08/ UR - http://www2007.org/paper570.php ER -