Presentation 2017-02-18
Proposal of extracting purchase behavior and product DNA using Topic Model
Mamoru Emoto, Yukio Ohsawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a method that enables us to extract customer characters and product characters based on customer purchase behavior. There are many proposed methods for clustering and extracting customer characters and their behavior but few methods focus on the fact that customer characters and product characters change as time advances. Therefore we apply Dynamic Topic Model(DTM), which is an extended model of Latent Dirichlet Allocation(LDA) and obtain customer and product vectors based on purchase behavior. These vectors are created from the output of DTM and by using them we can discuss and visualize their features on a field of customer purchase behavior topics. We also conduct an experiment at a supermarket store to validate hypotheses based on product vectors. From the result of the experiment, we can recognize that this method is promising for creating marketing strategies.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Point Of Sales / Topic Model / Visualization / Customer Behavior
Paper # AI2016-33
Date of Issue 2017-02-11 (AI)

Conference Information
Committee AI
Conference Date 2017/2/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Toshiharu Sugawara(Waseda Univ.)
Vice Chair Tsunenori Mine(Kyushu Univ.) / Daisuke Katagami(Tokyo Polytechnic Univ.)
Secretary Tsunenori Mine(Ritsumeikan Univ.) / Daisuke Katagami(Shizuoka Univ.)
Assistant Yuichi Sei(Univ. of Electro-Comm.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Proposal of extracting purchase behavior and product DNA using Topic Model
Sub Title (in English)
Keyword(1) Point Of Sales
Keyword(2) Topic Model
Keyword(3) Visualization
Keyword(4) Customer Behavior
1st Author's Name Mamoru Emoto
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Yukio Ohsawa
2nd Author's Affiliation The University of Tokyo(UTokyo)
Date 2017-02-18
Paper # AI2016-33
Volume (vol) vol.116
Number (no) AI-460
Page pp.pp.51-55(AI),
#Pages 5
Date of Issue 2017-02-11 (AI)