Search
 
loader loading subjects...
cover
Helping decision support with regression trees and clustering perturbation
Olivier Parisot, Yoann Didry, Thomas Tamisier
104 - 109
10.3233/978-1-61499-399-5-104
Frontiers in Artificial Intelligence and Applications
Volume 261: DSS 2.0 – Supporting Decision Making with New Technologies
Abstract

Regression trees are helpful tools for knowledge discovery and decision support, due to their simple structure and the easiness to obtain them from data. Nonetheless, when applied to non-trivial datasets, they tend to grow according to the complexity of the data, becoming uneasy to interpret. In this work, we propose a clustering perturbation method to reduce the size of the regression tree obtained from each cluster. A prototype has been developed and tested on several regression datasets.

$35.00 / €27.50 / £22.00
Add PDF to cart