A Product Feature-based User-Centric Ranking Model for E-Commerce Search

Lamjed Ben Jabeur; Laure Soulier; Lynda Tamine; Paul Mousset

A Product Feature-based User-Centric Ranking Model for E-Commerce Search

Lamjed Ben Jabeur ¹ Laure Soulier ^{2, *} Lynda Tamine ¹ Paul Mousset ¹

* Corresponding author

1 IRIT - Institut de recherche en informatique de Toulouse

2 MLIA - Machine Learning and Information Access

LIP6 - Laboratoire d'Informatique de Paris 6

Abstract : During the online shopping process, users search for interesting products in order to quickly access those that fit with their needs among a long tail of similar or closely related products. Our contribution addresses head queries that are frequently submitted on e-commerce Web sites. Head queries usually target featured products with several variations , accessories, and complementary products. We present in this paper a product feature-based user-centric model for product search involving, in addition to product characteristics, the user engagement toward the product. This model has been evaluated through the product search track of the LL4IR lab at CLEF 2015 in order to highlight the effectiveness of our model as well as the impact of the user engagement factor.

Keywords : user preferences user engagement ranking product search Information retrieval living labs LL4IR e-commerce

Document type :

Conference papers

Domain :

Computer Science [cs] / Information Retrieval [cs.IR]

Liste complète des métadonnées

Cited literature [20 references] Display Hide Download

https://hal.sorbonne-universite.fr/hal-01349111
Contributor : Laure Soulier <>
Submitted on : Friday, July 29, 2016 - 1:29:19 PM
Last modification on : Friday, April 12, 2019 - 4:23:06 PM

CLEF2016-BoL.pdf

Files produced by the author(s)

A Product Feature-based User-Centric Ranking Model for E-Commerce Search

File

Identifiers

Collections

Citation

Export

Metrics

463

199

Contact

A Product Feature-based User-Centric Ranking Model for E-Commerce Search

File

Identifiers

Collections

Citation

Export

Share

Metrics

463

199

Contact