e-Shop User Preferences via User Behavior

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F14%3A10277918" target="_blank" >RIV/00216208:11320/14:10277918 - isvavai.cz</a>
Result on the web
<a href="http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0005102300680075" target="_blank" >http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0005102300680075</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5220/0005102300680075" target="_blank" >10.5220/0005102300680075</a>

Result language
angličtina
Original language name
e-Shop User Preferences via User Behavior
Original language description
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. Asa future work we present richer data on time dependent user behavior.
Czech name
—
Czech description
—

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
ICE-B 2014 - Proceedings of the 11th International Conference on e-Business, Vienna, Austria, 28-30 August, 2014
ISBN
978-989-758-043-7
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
68-75
Publisher name
SciTePress
Place of publication
Neuveden
Event location
Vienna, Austria
Event date
Aug 28, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)