2nd Netflix-KDD Workshop Workshop on Large-Scale Recommender Systems and the Netflix Prize Competition Held in conjunction with The 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2008) August 24, 2008, Las Vegas, NV

Workshop Description

Recommender systems have emerged over the last several years as an important area of research spanning the boundaries of such diverse set of disciplines as data mining, machine learning, information retrieval, human-computer interaction, marketing and operations research. Interest in recommender systems was further enhanced when Netflix announced its $1,000,000 prize competition in October 2006 that attracted over 20,000 participants from 167 different countries. One of the sub-fields of recommender systems that benefited very significantly from the Netflix Prize competition is the area of large-scale recommender systems, which deals with scaling recommendation methods to large datasets. Many Netflix competitors came to realize that some of the well-known recommendation algorithms would not scale well to the Netflix dataset. In addition, some of the most popular and well-regarded methods would perform poorly on the Netflix dataset — maybe because the asymptotic performance of these methods is quite different from their performance on smaller datasets.

Workshop Topics

This workshop will address these scalability and performance issues by focusing on recommendation methods explicitly designed to handle large data sets. The topics of interest include (but are not limited to): Novel recommendation models, emphasizing accuracy, performance and asymptotic behavior Scalability problems in recommender systems Novel evaluation methodologies for recommendation quality Efficient integration of multiple complementary predictors Studies of content-filtering vs. collaborative filtering and their integration in large-scale environments Explaining and presenting recommendations to end-users Idiosyncrasies of the Netflix Prize Dataset and lessons learned from its analysis Netflix Prize competition at large

Paper Submission

We invite the submission of papers on these and related topics by researchers in the recommender systems field as well as the participants of the Netflix Prize competition. All submitted papers will be evaluated by the workshop program committee based on scientific merits and novelty as perceived by the committee. Accepted papers will appear in the workshop proceedings. At least one author of each accepted paper is expected to register for the workshop and present the paper. The papers may be submitted either as full or short papers. The page limit for a full paper is 8 pages and for a short paper is 4 pages inclusive of all references and figures. All submitted papers must be in the PDF format and use standard templates that can be found here. Please submit your manuscript in PDF format at the paper submission website.

Important Dates

May 30, 2008: Electronic submission of full papers & abstracts June 27, 2008: Author notification July 7, 2008: Submission of Camera-ready papers August 24, 2008: Workshop in Las Vegas, California

Workshop Co-Chairs

Alex Tuzhilin (chair), NYU Stern . E-mail: atuzhili @ stern.nyu.edu Yehuda Koren (co-chair), AT&T Labs--Research. E-mail: yehuda @ research.att.com Jim Bennett, Netflix. E-mail: jbennett @ netflix.com Charles Elkan, University of California, San Diego. E-mail: elkan @ cs.ucsd.edu Daniel Lemire, University of Quebec at Montreal (UQAM). E-mail: lemire @ acm.org

Disclaimer: To avoid conflict of interest, participants in the Netflix Prize competition will not handle submitted papers, and will not be involved in the paper selection and reviewing process.