TY - JOUR
T1 - An experimental study on re-ranking web shop search results using semantic segmentation of user profiles
AU - Poppink, Bram
AU - Frasincar, Flavius
AU - Robal, Tarmo
N1 - Publisher Copyright:
© 2023 Elsevier B.V.
PY - 2023/11/1
Y1 - 2023/11/1
N2 - Although purchasing online has become increasingly popular, finding suitable products in Web shop environments still requires significant effort from users. This study proposes a method for re-ranking products on a Web shop's search engine to better match individual user preferences using semantic descriptions in user profiles. Through a live experiment, we demonstrate that the proposed re-ranking method incorporating segment-based customer preferences increases the commercial efficiency of Web shop's search engine, increases the average rank of product clicks and the add-to-basket rate, while decreases the click-through rate. Interestingly and contrary to what holds for Web search, the empirical evidence collected in this study indicates that the average rank of clicks used to measure the quality of Web search may not be a reliable indicator for the product search result ranking quality for product search engines in Web shop environments.
AB - Although purchasing online has become increasingly popular, finding suitable products in Web shop environments still requires significant effort from users. This study proposes a method for re-ranking products on a Web shop's search engine to better match individual user preferences using semantic descriptions in user profiles. Through a live experiment, we demonstrate that the proposed re-ranking method incorporating segment-based customer preferences increases the commercial efficiency of Web shop's search engine, increases the average rank of product clicks and the add-to-basket rate, while decreases the click-through rate. Interestingly and contrary to what holds for Web search, the empirical evidence collected in this study indicates that the average rank of clicks used to measure the quality of Web search may not be a reliable indicator for the product search result ranking quality for product search engines in Web shop environments.
UR - https://www.scopus.com/pages/publications/85172125462
U2 - 10.1016/j.elerap.2023.101310
DO - 10.1016/j.elerap.2023.101310
M3 - Article
AN - SCOPUS:85172125462
SN - 1567-4223
VL - 62
JO - Electronic Commerce Research and Applications
JF - Electronic Commerce Research and Applications
M1 - 101310
ER -