Presentation 2007-05-31
Personalized Recommendation by Identifying Innovator
Noriaki KAWAMAE, Takeshi YAMADA, Naonori UEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To improve the predictive performance of personalized recommendation systems, we propose a personalized ranking method based on a new user-user relationship measure. We assume that the behavior of an active user can be predicted from the behavior history of like-minded innovators, who share the interests of the user and behave earlier than the user. To identify these innovators, we define the Relative Innovator Degree (RID) that is the innovator degree of any user with respect to a given active user, and that allows us to evaluate how likely it is that the active user would select him/her. We also consider the indirect propagation effect of RID influences by simulating users recursively selecting and, and incorporate this notion in the proposed method. The list of top N candidate contents for recommendation is obtained by summarizing the preferences of all influential users. Experiments using real online sales data show that the proposed method significantly outperforms existing methods in terms of precision, especially when the recursive propagation effects are incorporated.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Personalization / Ranking / Recommendation / Prediction / Innovator
Paper # AI2007-4
Date of Issue

Conference Information
Committee AI
Conference Date 2007/5/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Personalized Recommendation by Identifying Innovator
Sub Title (in English)
Keyword(1) Personalization
Keyword(2) Ranking
Keyword(3) Recommendation
Keyword(4) Prediction
Keyword(5) Innovator
1st Author's Name Noriaki KAWAMAE
1st Author's Affiliation NTT Communication Science Laboratories()
2nd Author's Name Takeshi YAMADA
2nd Author's Affiliation NTT Communication Science Laboratories
3rd Author's Name Naonori UEDA
3rd Author's Affiliation NTT Communication Science Laboratories
Date 2007-05-31
Paper # AI2007-4
Volume (vol) vol.107
Number (no) 78
Page pp.pp.-
#Pages 6
Date of Issue