Using Glocal Event Alignment for Comparing Sequences of Significantly Different Lengths - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Using Glocal Event Alignment for Comparing Sequences of Significantly Different Lengths

Résumé

This work takes place in the context of conversion rate optimization by enhancing the user experience during navigation on ecommerce web sites. The requirement is to be able to segment visitors into meaningful clusters, which can then be targeted with specific call-to-actions, in order to increase the web site turnover. This paper presents an original approach, which equally combines global-and localalignment techniques (Needleman-Wunsch and Smith-Waterman) in order to automatically segment visitors according to the sequence of visited pages. Experimental results on synthetic datasets show that our approach out-performs other typically used alignment metrics, such as hybrid approaches or Dynamic Time Warping.
Fichier principal
Vignette du fichier
mldm2016.pdf (427.53 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03807693 , version 1 (10-10-2022)

Identifiants

Citer

Vinh-Trung Luu, Mathis Ripken, Germain Forestier, Frédéric Fondement, Pierre-Alain Muller. Using Glocal Event Alignment for Comparing Sequences of Significantly Different Lengths. Machine Learning and Data Mining in Pattern Recognition (MLDM), Jul 2016, New York City, United States. pp.58-72, ⟨10.1007/978-3-319-41920-6_5⟩. ⟨hal-03807693⟩

Collections

SITE-ALSACE IRIMAS
10 Consultations
17 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More