標題: Implications of the Dirichlet assumption for discretization of continuous variables in naive Bayesian classifiers
作者: Hsu, CN
Huang, HJ
Wong, TT
資訊工程學系
Department of Computer Science
關鍵字: naive Bayesian classifiers;Dirichlet distributions;perfect aggregation;continuous variables;discretization;lazy discretization;interval data
公開日期: 1-十二月-2003
摘要: In a naive Bayesian classifier, discrete variables as well as discretized continuous variables are assumed to have Dirichlet priors. This paper describes the implications and applications of this model selection choice. We start by reviewing key properties of Dirichlet distributions. Among these properties, the most important one is "perfect aggregation," which allows us to explain why discretization works for a naive Bayesian classifier. Since perfect aggregation holds for Dirichlets, we can explain that in general, discretization can outperform parameter estimation assuming a normal distribution. In addition, we can explain why a wide variety of well-known discretization methods, such as entropy-based, ten-bin, and bin-log l, can perform well with insignificant difference. We designed experiments to verify our explanation using synthesized and real data sets and showed that in addition to well-known methods, a wide variety of discretization methods all perform similarly. Our analysis leads to a lazy discretization method, which discretizes continuous variables according to test data. The Dirichlet assumption implies that lazy methods can perform as well as eager discretization methods. We empirically confirmed this implication and extended the lazy method to classify set-valued and multi-interval data with a naive Bayesian classifier.
URI: http://dx.doi.org/10.1023/A:1026367023636
http://hdl.handle.net/11536/27341
ISSN: 0885-6125
DOI: 10.1023/A:1026367023636
期刊: MACHINE LEARNING
Volume: 53
Issue: 3
起始頁: 235
結束頁: 263
顯示於類別:期刊論文


文件中的檔案:

  1. 000186206000002.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。