G. Webb, J. Boughton, and Z. Wang. Proceedings of the First Australasian Data Mining Workshop (AusDM02), page 65-73. Sydney, University of Technology, (2002)
Abstract
Naive Bayes is a simple, computationally efficient and remarkably accurate approach to classification learning. These properties have led to its wide deployment in many online applications. However, it is based on an assumption that all attributes are conditionally independent given the class. This assumption leads to decreased accuracy in some applications. AODE overcomes the attribute independence assumption of naive Bayes by averaging over all models in which all attributes depend upon the class and a single other attribute. The resulting classification learning algorithm for nominal data is computationally efficient and achieves very low error rates.
%0 Conference Paper
%1 WebbBoughtonWang02
%A Webb, G. I.
%A Boughton, J.
%A Wang, Z.
%B Proceedings of the First Australasian Data Mining Workshop (AusDM02)
%C Sydney
%D 2002
%E Simoff, S.J
%E Williams, G.J
%E Hegland, M.
%I University of Technology
%K Conditional Estimation,AODE Probability
%P 65-73
%T Averaged One-Dependence Estimators: Preliminary Results
%X Naive Bayes is a simple, computationally efficient and remarkably accurate approach to classification learning. These properties have led to its wide deployment in many online applications. However, it is based on an assumption that all attributes are conditionally independent given the class. This assumption leads to decreased accuracy in some applications. AODE overcomes the attribute independence assumption of naive Bayes by averaging over all models in which all attributes depend upon the class and a single other attribute. The resulting classification learning algorithm for nominal data is computationally efficient and achieves very low error rates.
@inproceedings{WebbBoughtonWang02,
abstract = {Naive Bayes is a simple, computationally efficient and remarkably accurate approach to classification learning. These properties have led to its wide deployment in many online applications. However, it is based on an assumption that all attributes are conditionally independent given the class. This assumption leads to decreased accuracy in some applications. AODE overcomes the attribute independence assumption of naive Bayes by averaging over all models in which all attributes depend upon the class and a single other attribute. The resulting classification learning algorithm for nominal data is computationally efficient and achieves very low error rates.},
added-at = {2016-03-20T05:42:04.000+0100},
address = {Sydney},
audit-trail = {*},
author = {Webb, G. I. and Boughton, J. and Wang, Z.},
biburl = {https://www.bibsonomy.org/bibtex/2e9fc278973aa6cef03b14f783c231678/giwebb},
booktitle = {Proceedings of the First Australasian Data Mining Workshop (AusDM02)},
editor = {Simoff, S.J and Williams, G.J and Hegland, M.},
interhash = {583e04181dfe58f8612c505a0b2b1d7b},
intrahash = {e9fc278973aa6cef03b14f783c231678},
keywords = {Conditional Estimation,AODE Probability},
location = {Canberra, Australia},
pages = {65-73},
publisher = {University of Technology},
timestamp = {2016-03-20T05:42:04.000+0100},
title = {Averaged One-Dependence Estimators: Preliminary Results},
year = 2002
}