Modeling Personal Preferences on Commodities by Behavior Log Analysis with Ubiquitous Sensing

  • Naoki Imamura
  • Akihiro Ogino
  • Toshikazu Kato
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5612)


Consumers may take some specific behavior preference or favorite items to get more information, such as the material and the price, in shopping. We have been developing a smart room to estimate their preference and favorite items through observation using ubiquitous sensors, such as RFID and Web cameras. We assumed the decision decision-making process in shopping as AIDMA rule, and detected specific behavior, which are “See”, “Touch” and “Take”, to estimate user’s interest. We found that we can classify consumers by their behavior patterns of the times and duration of the behaviors. In our experiment we have tested twenty-eight subjects on twenty-four T-shirts. In the experiment, we got better precision ratio for each subjects on estimating preference and favorite items by discriminate analysis on his or her behavior log, and behavior patterns classification above.


Behavior Pattern Action Frequency Background Image Favorite Item Comparison Type 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kazuhide, H., Yo-iti, W., Sae-ueng, S., Katayama, T., Nobuyoshi, H., Nagase, H., Toshikazu, K.: Design of Ubiquitous Information Environment with Real World Interaction and Modeling KANSEI Facilities, vol. 103, ISSN:09135685Google Scholar
  2. 2.
  3. 3.
    Onodera, K., Yusaku, K.: Why would someone buy in this store. Publisher Nihon Keizai Shimbun (2005)Google Scholar
  4. 4.
    Koshizuka, S.: Ubiquitous ID technology and its applications. IEICE 87(5), 374–378 (2004)Google Scholar
  5. 5.
    Sae-ueng, S., Pinyapong, S., Ogino, A., Kato, T.: Consumer friendly Shopping Assistance by Personal Behavior Log Analysis on Ubiquitous Shop Space. In: Proceeding of 2nd IEEE Asia-Pacific Services Computer Conference, APSCCS 2007, pp. 496–503 (2007)Google Scholar
  6. 6.
    Sae-ueng, S., Pinyapong, S., Ogino, A., Kato, T.: Modeling personal preference using shopping behaviors in ubiquitous information environment. In: Proceeding of 18th IEICE data engineering workshop /5th DBSJ annual meeting (DEWS 2007) (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Naoki Imamura
    • 1
  • Akihiro Ogino
    • 2
  • Toshikazu Kato
    • 3
  1. 1.Graduate School of Chuo UniversityTokyoJapan
  2. 2.Kyoto Sangyo University, Kamigamomotoyama Kita-kuKyoto-si, KyotoJapan
  3. 3.Chuo UniversityTokyoJapan

Personalised recommendations