Des séquences aux tendances

Céline Fiot 1 Florent Masseglia 1 Anne Laurent 2 Maguelonne Teisseire 2
1 AxIS - Usage-centered design, analysis and improvement of information systems
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Paris-Rocquencourt
2 TATOO - Fouille de données environnementales
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Temporal data can be handled by different techniques for discovering specific knowl- edge. Sequential pattern mining allows discovering frequent sequences embedded in temporally annotated records. In the access data of a Web site, one may, for instance, discover that “5% of the users request the page register.php and then request the page help.html”. However, se- quential patterns do not allow extracting temporal tendencies. By means of temporal tendency mining, one may discover in the same access data that “An increasing number of requests to registration.php during a short period preceeds an increasing number of requests to faq.html, after a very short period”. In this paper, we define evolution patterns that allow discovering such knowledge. We define evolution patterns and introduce our algorithms TED and EVA.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00273920
Contributor : Celine Fiot <>
Submitted on : Wednesday, October 9, 2019 - 10:39:51 AM
Last modification on : Wednesday, October 9, 2019 - 5:10:30 PM

File

lirmm-00273920v1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00273920, version 1

Citation

Céline Fiot, Florent Masseglia, Anne Laurent, Maguelonne Teisseire. Des séquences aux tendances. INFORSID: INFormatique des ORganisations et Systèmes d’Information et de Décision, May 2008, Fontainebleau, France. ⟨lirmm-00273920⟩

Share

Metrics

Record views

170

Files downloads

4