Show simple item record

dc.contributor.authorBifet Figuerol, Albert Carles
dc.contributor.authorHolmes, Geoffrey
dc.contributor.authorPfahringer, Bernhard
dc.contributor.authorKirkby, R
dc.contributor.authorGavaldà Mestre, Ricard
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Ciències de la Computació
dc.date.accessioned2018-11-28T18:03:01Z
dc.date.issued2009
dc.identifier.citationBifet, A.C., Holmes, G., Pfahringer, B., Kirkby, R., Gavaldà, R. New ensemble methods for evolving data streams. A: ACM SIGKDD Conference on Knowledge Discovery and Data Mining. "KDD'09: proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: June 28-July 1, 2009: Paris, France". New York: Association for Computing Machinery (ACM), 2009, p. 139-148.
dc.identifier.isbn978-1-60558-495-9
dc.identifier.urihttp://hdl.handle.net/2117/125201
dc.description.abstractAdvanced analysis of data streams is quickly becoming a key area of data mining research as the number of applications demanding such processing increases. Online mining when such data streams evolve over time, that is when concepts drift or change completely, is becoming one of the core issues. When tackling non-stationary concepts, ensembles of classifiers have several advantages over single classifier methods: they are easy to scale and parallelize, they can adapt to change quickly by pruning under-performing parts of the ensemble, and they therefore usually also generate more accurate concept descriptions. This paper proposes a new experimental data stream framework for studying concept drift, and two new variants of Bagging: ADWIN Bagging and Adaptive-Size Hoeffding Tree (ASHT) Bagging. Using the new experimental framework, an evaluation study on synthetic and real-world datasets comprising up to ten million examples shows that the new ensemble methods perform very well compared to several known methods.
dc.format.extent10 p.
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Sistemes d'informació::Bases de dades
dc.subject.lcshData mining
dc.subject.otherData streams
dc.subject.otherEnsemble methods
dc.subject.otherConcept drift
dc.subject.otherDecision trees
dc.titleNew ensemble methods for evolving data streams
dc.typeConference report
dc.subject.lemacMineria de dades
dc.contributor.groupUniversitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge
dc.identifier.doi10.1145/1557019.1557041
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://dl.acm.org/citation.cfm?doid=1557019.1557041
dc.rights.accessRestricted access - publisher's policy
drac.iddocument2339605
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/MEC/5PN/TIN2005-08832-C03-03
dc.date.lift10000-01-01
upcommons.citation.authorBifet, A.C., Holmes, G., Pfahringer, B., Kirkby, R., Gavaldà, R.
upcommons.citation.contributorACM SIGKDD Conference on Knowledge Discovery and Data Mining
upcommons.citation.pubplaceNew York
upcommons.citation.publishedtrue
upcommons.citation.publicationNameKDD'09: proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: June 28-July 1, 2009: Paris, France
upcommons.citation.startingPage139
upcommons.citation.endingPage148


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder