Show simple item record  

dc.contributor.authorHolmes, Geoffrey
dc.contributor.authorKirkby, Richard Brendon
dc.contributor.authorPfahringer, Bernhard
dc.coverage.spatialConference held at Portugalen_NZ
dc.identifier.citationHolmes, G., Kirkby, R. & Pfahringer, B. (2005). Stress- testing Hoeffding trees . In A. Jorge et al. (Eds.), Proceedings of the 9th European Conference on Principles and Practice of Knowledge Discovery in Databases, Porto, Portugal, October 3-7, 2005. (pp. 495-502). Berlin: Springer.en_US
dc.description.abstractHoeffding trees are state-of-the-art in classification for data streams. They perform prediction by choosing the majority class at each leaf. Their predictive accuracy can be increased by adding Naive Bayes models at the leaves of the trees. By stress-testing these two prediction methods using noise and more complex concepts and an order of magnitude more instances than in previous studies, we discover situations where the Naive Bayes method outperforms the standard Hoeffding tree initially but is eventually overtaken. The reason for this crossover is determined and a hybrid adaptive method is proposed that generally outperforms the two original prediction methods for both simple and complex concepts as well as under noise.en_US
dc.publisherSpringer, Berlinen_US
dc.sourcePKDD 2005en_NZ
dc.subjectcomputer scienceen_US
dc.subjectHoeffding treesen_US
dc.subjectMachine learning
dc.titleStress- testing Hoeffding treesen_US
dc.typeConference Contributionen_US
dc.relation.isPartOfProc 9th European Conference on Principles and Practice of Knowledge Discovery in Databasesen_NZ
pubs.volumeLNCS 3721en_NZ

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record