Distributed collaborative filtering with domain specialization

Shlomo Berkvosky, Tsvi Kuflik, Francesco Ricci

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


User data scarcity has always been indicated among the major problems of collaborative filtering recommender systems. That is, if two users do not share sufficiently large set of items for whom their ratings are known, then the user-to-user similarity computation is not reliable and a rating prediction for one user can not be based on the ratings of the other. This paper shows that this problem can be solved, and that the accuracy of collaborative recommendations can be improved by: a) partitioning the collaborative user data into specialized and distributed repositories, and b) aggregating information coming from these repositories. This paper explores a content-dependent partitioning of collaborative movie ratings, where the ratings are partitioned according to the genre of the movie and presents an evaluation of four aggregation approaches. The evaluation demonstrates that the aggregation improves the accuracy of a centralized system containing the same ratings and proves the feasibility and advantages of a distributed collaborative filtering scenario.

Original languageEnglish
Title of host publicationRecSys'07
Subtitle of host publicationProceedings of the 2007 ACM Conference on Recommender Systems
Number of pages8
StatePublished - 2007
EventRecSys'07: 2007 1st ACM Conference on Recommender Systems - Minneapolis, MN, United States
Duration: 19 Oct 200720 Oct 2007

Publication series

NameRecSys'07: Proceedings of the 2007 ACM Conference on Recommender Systems


ConferenceRecSys'07: 2007 1st ACM Conference on Recommender Systems
Country/TerritoryUnited States
CityMinneapolis, MN


  • Distributed collaborative filtering
  • Mediation of user modeling data
  • Recommender systems

ASJC Scopus subject areas

  • Computer Science (all)


Dive into the research topics of 'Distributed collaborative filtering with domain specialization'. Together they form a unique fingerprint.

Cite this