Presentation 2017-03-10
Probabilistic Inference of Customer States Using Statistical Open Data and Bayesian Networks
Hiroaki Nakamura, Michiharu Kudo, Hironori Takeuchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Enterprises need to provide services specialized for each customer in a timely manner, and for that purpose, they rely on information such as customer profile and purchase history. However, in many cases, they do not have enough customer data for service personalization. To overcome the limitation, use of open data for predicting customer information is a promising approach. Especially the governments of many countries have recently started providing online a variety of survey results as statistical data. In this paper, we investigate Bayesian Network approach for predicting unknown customer information from known facts and statistical data.We also introduce a method for predicting customer life events by analyzing multiple statistical data, and that for combining microdata and summary data to complement each other.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Probabilistic Inference / Open Data / Statistical Data / Bayesian Networks
Paper # SC2016-35
Date of Issue 2017-03-03 (SC)

Conference Information
Committee SC
Conference Date 2017/3/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English) National Institute of Informatics
Topics (in Japanese) (See Japanese page)
Topics (in English) Smart System Applications, etc.
Chair Incheon Paik(Univ. of Aizu)
Vice Chair Masahide Nakamura(Kobe Univ.)
Secretary Masahide Nakamura(NICT)

Paper Information
Registration To Technical Committee on Service Computing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Probabilistic Inference of Customer States Using Statistical Open Data and Bayesian Networks
Sub Title (in English)
Keyword(1) Probabilistic Inference
Keyword(2) Open Data
Keyword(3) Statistical Data
Keyword(4) Bayesian Networks
1st Author's Name Hiroaki Nakamura
1st Author's Affiliation IBM Japan, Ltd.(IBM Japan)
2nd Author's Name Michiharu Kudo
2nd Author's Affiliation IBM Japan, Ltd.(IBM Japan)
3rd Author's Name Hironori Takeuchi
3rd Author's Affiliation IBM Japan, Ltd.(IBM Japan)
Date 2017-03-10
Paper # SC2016-35
Volume (vol) vol.116
Number (no) SC-518
Page pp.pp.39-44(SC),
#Pages 6
Date of Issue 2017-03-03 (SC)