Show simple item record  

dc.contributor.authorHall, Mark A.
dc.contributor.authorFrank, Eibe
dc.coverage.spatialConference held at Coconut Grove, Florida, USAen_NZ
dc.date.accessioned2009-01-12T22:28:18Z
dc.date.available2009-01-12T22:28:18Z
dc.date.issued2008
dc.identifier.citationHall, M. & Frank, E.(2008). Combining Naive Bayes and Decision Tables. In D.L. Wilson & H. Chad (Eds), Proceedings of Twenty-First International Florida Artificial Intelligence Research Society Conference, AAAI Press, Coconut Grove, Florida, USA, 15-17 May, 2008(pp. 318-319).en
dc.identifier.urihttps://hdl.handle.net/10289/1773
dc.description.abstractWe investigate a simple semi-naive Bayesian ranking method that combine naive Bayes with induction of decision tables. Naive Bayes and decision tables can both be trained efficientyly, and the same holds true for the combined semi-naive model. We show that the resulting ranker, compared to either component technique, frequently significantly increases AUC. For some datasets it significantly improves on both techniques. This is also the case when attribute selection is performed in naive Bayes and its semi-naive variant.en
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherAAAI Pressen
dc.relation.urihttp://www.aaai.org/Library/FLAIRS/2008/flairs08-076.phpen
dc.rightsThis is an article published in Proceedings of Twenty-First International Florida Artificial Intelligence Research Society Conference, AAAI Press, Coconut Grove, Florida, USA, 15-17 May, 2008.en
dc.subjectcomputer scienceen
dc.subjectBayesian networken
dc.subjectdecision tableen
dc.subjectMachine learning
dc.titleCombining Naive Bayes and Decision Tablesen
dc.typeConference Contributionen
dc.relation.isPartOfProc 21st International Florida Artificial Intelligence Research Society Conferenceen_NZ
pubs.begin-page318en_NZ
pubs.elements-id17972
pubs.end-page319en_NZ
pubs.finish-date2008-05-17en_NZ
pubs.start-date2008-05-15en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record