Show simple item record

dc.contributor.authorAuret, L.
dc.contributor.authorAldrich, Chris
dc.date.accessioned2017-01-30T15:33:36Z
dc.date.available2017-01-30T15:33:36Z
dc.date.created2012-02-29T20:00:43Z
dc.date.issued2011
dc.identifier.citationAuret, Lidia and Aldrich, Chris. 2011. Empirical comparison of tree ensemble variable importance measures. Chemometrics and Intelligent Laboratory Systems. 105 (2): pp. 157-170.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/47469
dc.identifier.doi10.1016/j.chemolab.2010.12.004
dc.description.abstract

Tree ensembles are becoming well-established as popular and powerful data modelling techniques. Tree ensemble models are essentially black box models, although their individual members may not be, and with their growing popularity, interest in the interpretation of tree ensemble models has also grown. This study presents variable importance measures associated with random forests, conditional inference forests and boosted trees, and employs a number of simulated data sets to compare these methods. Overall, variable importance indicators based on bagged conditional inference forests appear to strike a good balance between identification of significant variables and avoiding unnecessary flagging of correlated variables. Data preprocessing and interpretation by experts knowledgeable with a specific data set remain vital.

dc.publisherELSEVIER
dc.subjectDecision trees
dc.subject- Variable importance
dc.subject- Ensemble learning
dc.subject- Random forests
dc.subject- Fault identification
dc.subject- Boosted trees
dc.subject- Conditional inference forests
dc.titleEmpirical comparison of tree ensemble variable importance measures
dc.typeJournal Article
dcterms.source.volume105
dcterms.source.startPage157
dcterms.source.endPage170
dcterms.source.issn0169-7439
dcterms.source.titleChemometrics and Intelligent Laboratory Systems
curtin.departmentWASM Minerals Engineering and Extractive Metallurgy Teaching Area
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record