Supervised and unsupervised discretization of continuous features

DMCA

Supervised and unsupervised discretization of continuous features (1995)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by James Dougherty , Ron Kohavi , Mehran Sahami

Venue:	in A. Prieditis & S. Russell, eds, Machine Learning: Proceedings of the Twelfth International Conference
Citations:	540 - 11 self

BibTeX

@INPROCEEDINGS{Dougherty95supervisedand,
    author = {James Dougherty and Ron Kohavi and Mehran Sahami},
    title = {Supervised and unsupervised discretization of continuous features},
    booktitle = {in A. Prieditis & S. Russell, eds, Machine Learning: Proceedings of the Twelfth International Conference},
    year = {1995},
    pages = {194--202},
    publisher = {Morgan Kaufmann}
}

OpenURL

Abstract

Many supervised machine learning algorithms require a discrete feature space. In this paper, we review previous work on continuous feature discretization, identify de n-ing characteristics of the methods, and conduct an empirical evaluation of several methods. We compare binning, an unsupervised discretization method, to entropy-based and purity-based methods, which are supervised algorithms. We found that the performance of the Naive-Bayes algorithm signi cantly improved when features were discretized using an entropy-based method. In fact, over the 16 tested datasets, the discretized version of Naive-Bayes slightly outperformed C4.5 on average. We also show that in some cases, the performance of the C4.5 induction algorithm signi cantly improved if features were discretized in advance � in our experiments, the performance never signi cantly degraded, an interesting phenomenon considering the fact that C4.5 is capable of locally discretizing features. 1

Keyphrases

unsupervised discretization continuous feature unsupervised discretization method purity-based method n-ing characteristic machine learning algorithm discretized version continuous feature discretization interesting phenomenon naive-bayes algorithm signi tested datasets induction algorithm signi several method entropy-based method discrete feature space previous work empirical evaluation

DMCA