Presentation 2012-11-07
Recommendation with User Stereotyping
Tatsuya OSAME, Jun SAKUMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Prediction accuracy of recommendation algorithm with user-item rating matrices can be improved by making use of user attributes as auxiliary information. However, attribute information, such as age and occupation, often takes discrete or categorical values. In this manuscript, we introduce user stereotyping method which allows to incorporate discrete or categorical user attribute information into recommendation algorithms. Stereotypes represent a group which contains relatively small number of users commonly having a few user attributes. Our method transforms user-item rating matrix into stereotype-item rating matrix. Thus, user attribute information is embedded into stereotype-item rating matrices. In the experiments, we present that prediction accuracy can be improved by user stereotyping.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) collaborative filtering / matrix factorization / recommendation system / stereotyping / hierarchical clustering
Paper # IBISML2012-63
Date of Issue

Conference Information
Committee IBISML
Conference Date 2012/10/31(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Information-Based Induction Sciences and Machine Learning (IBISML)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recommendation with User Stereotyping
Sub Title (in English)
Keyword(1) collaborative filtering
Keyword(2) matrix factorization
Keyword(3) recommendation system
Keyword(4) stereotyping
Keyword(5) hierarchical clustering
1st Author's Name Tatsuya OSAME
1st Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Jun SAKUMA
2nd Author's Affiliation Japan Science and Technology Agency
Date 2012-11-07
Paper # IBISML2012-63
Volume (vol) vol.112
Number (no) 279
Page pp.pp.-
#Pages 8
Date of Issue