An Incremental Method for Finding Multivariate Splits for Decision Trees
Abstract
Decision trees that are limited to testing a single variable at a node are potentially much larger than trees that allow testing multiple variables at a node. This limitation reduces the ability to express concepts succinctly, which renders many classes of concepts difficult or impossible to express. This paper presents the PT2 algorithm, which searches for a multivariate split at each node. Because a univariate test is a special case of a multivariate test, the expressive power of such decision trees is strictly increased. The algorithm is incremental, handles ordered and unordered variables, and estimates missing values.
Cite
Text
Utgoff and Brodley. "An Incremental Method for Finding Multivariate Splits for Decision Trees." International Conference on Machine Learning, 1990. doi:10.1016/B978-1-55860-141-3.50011-0Markdown
[Utgoff and Brodley. "An Incremental Method for Finding Multivariate Splits for Decision Trees." International Conference on Machine Learning, 1990.](https://mlanthology.org/icml/1990/utgoff1990icml-incremental/) doi:10.1016/B978-1-55860-141-3.50011-0BibTeX
@inproceedings{utgoff1990icml-incremental,
title = {{An Incremental Method for Finding Multivariate Splits for Decision Trees}},
author = {Utgoff, Paul E. and Brodley, Carla E.},
booktitle = {International Conference on Machine Learning},
year = {1990},
pages = {58-65},
doi = {10.1016/B978-1-55860-141-3.50011-0},
url = {https://mlanthology.org/icml/1990/utgoff1990icml-incremental/}
}