e-Shop User Preferences via User Behavior

Peter Vojtáš, Ladislav Peška

Abstract

We deal with the problem of using user behavior for business relevant analytic task processing. We describe our acquaintance with preference learning from behavior data from an e-shop. Based on our experience and problems we propose a model for collecting (java script tracking) and processing user behavior data. We present several results of offline experiments on real production data. We show that mere data on users (implicit) behavior are sufficient for improvement of prediction of user preference. As a future work we present richer data on time dependent user behavior.

References

  1. Eckhardt, A. Prefwork - a framework for user preference learning methods testing. In Proceedings of ITAT 2009 Information Technologies - Applications and Theory, Slovakia. CEUR-WS, 7-13
  2. Eckhardt, A., 2012. PrefWork - a framework for testing methods for user preference learning. http://code.google.com/p/prefwork/
  3. Eckhardt, A. & Vojtas, P. Considering Data Mining Techniques in User Preference Learning, In Proc. 2008 IEEE/WIC/ACM IC WI-IAT, IEEE, 33 - 36
  4. Holland, S. & Ester, M. & Kiessling, W. Preference mining: A novel approach on mining user preferences for personalized applications. In Knowledge Discovery in Databases: PKDD 2003, Springer Berlin / Heidelberg, 2003, 204-216
  5. Kelly, D. & Teevan, J., 2003. Implicit feedback for inferring user preference: a bibliography. Newsletter ACM SIGIR Forum, 37.2 ,18 - 28.
  6. Nichols, D.M. Implicit rating and filtering. In Proceedings of 5th DELOS Workshop on Filtering and Collaborative Filtering . Budapest, ERCIM 1997
  7. Peska, L. & Eckhardt, A. & Vojtas, P. Upcomp - a php component for recommendation based on user behavior. In Proc. 2011 IEEE/WIC/ACM IC WI-IAT, IEEE, 306-309
  8. Shearer, C. , 2000. The CRISP-DM model: the new blueprint for data mining, J Data Warehousing 5 , 13-22
  9. Sourceforge, SMO Classifier, http://weka.sourceforge.net/ doc.dev/ weka/classifiers/functions/SMOreg.html, last visited 05/07/2014
  10. Sourceforge, M5P Classifier, http://weka.sourceforge.net/ doc.dev/weka/classifiers/trees/M5P.html, last visited 05/07/2014
  11. Wikipedia, Kendall tau rank correlation coefficient, http://en.wikipedia.org/wiki/Kendall_tau_rank_ correlation_ coefficient, last visited 05/07/2014
Download


Paper Citation


in Harvard Style

Vojtáš P. and Peška L. (2014). e-Shop User Preferences via User Behavior . In Proceedings of the 11th International Conference on e-Business - Volume 1: ICE-B, (ICETE 2014) ISBN 978-989-758-043-7, pages 68-75. DOI: 10.5220/0005102300680075


in Bibtex Style

@conference{ice-b14,
author={Peter Vojtáš and Ladislav Peška},
title={e-Shop User Preferences via User Behavior},
booktitle={Proceedings of the 11th International Conference on e-Business - Volume 1: ICE-B, (ICETE 2014)},
year={2014},
pages={68-75},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005102300680075},
isbn={978-989-758-043-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th International Conference on e-Business - Volume 1: ICE-B, (ICETE 2014)
TI - e-Shop User Preferences via User Behavior
SN - 978-989-758-043-7
AU - Vojtáš P.
AU - Peška L.
PY - 2014
SP - 68
EP - 75
DO - 10.5220/0005102300680075