Social collaborative filtering for cold-start recommendations

Suvash Sedhain*, Scott Sanner, Darius Braziunas, Lexing Xie, Jordan Christensen

*Corresponding author for this work

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

    98 Citations (Scopus)


    We examine the cold-start recommendation task in an online retail setting for users who have not yet purchased (or interacted in a meaningful way with) any available items but who have granted access to limited side information, such as basic demographic data (gender, age, location) or social network information (Facebook friends or page likes). We formalize neighborhood-based methods for cold-start collaborative filtering in a generalized matrix algebra framework that does not require purchase data for target users when their side information is available. In real-data experiments with 30,000 users who purchased 80,000+ books and had 9,000,000+ Facebook friends and 6,000,000+ page likes, we show that using Facebook page likes for cold-start recommendation yields up to a 3-fold improvement in mean average precision (mAP) and up to 6-fold improvements in Precision@k and Recall@k compared to most-popular-item, demographic, and Facebook friend cold-start recommenders. These results demonstrate the substantial predictive power of social network content, and its significant utility in a challenging problem - recommendation for cold-start users.

    Original languageEnglish
    Title of host publicationRecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems
    PublisherAssociation for Computing Machinery
    Number of pages4
    ISBN (Electronic)9781450326681
    Publication statusPublished - 6 Oct 2014
    Event8th ACM Conference on Recommender Systems, RecSys 2014 - Foster City, United States
    Duration: 6 Oct 201410 Oct 2014

    Publication series

    NameRecSys 2014 - Proceedings of the 8th ACM Conference on Recommender Systems


    Conference8th ACM Conference on Recommender Systems, RecSys 2014
    Country/TerritoryUnited States
    CityFoster City


    Dive into the research topics of 'Social collaborative filtering for cold-start recommendations'. Together they form a unique fingerprint.

    Cite this