search for




 

Model based hybrid decision tree
Journal of the Korean Data & Information Science Society 2019;30:515-24
Published online May 31, 2019;  https://doi.org/10.7465/jkdi.2019.30.3.515
© 2019 Korean Data and Information Science Society.

Youtaek Jeon1 · HyungJun Cho2

12Department of Statistics, Korea University
Correspondence to: Professor, Department of Statistics, Korea University, 145, Anam-ro, Seongbukgu, Seoul 02841, Korea. E-mail: hj4cho@korea.ac.kr
This research was supported by a Korea University Grant(K1707561) and Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education( 2018R1D1A1B07044479).
Received January 17, 2019; Revised April 5, 2019; Accepted April 12, 2019.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Decision trees can categorize or predict target objects by dividing given predictor spaces into several simple rectangular spaces. Decision-making trees have the advantages of being easy to use, understand and explain. However, it tends to have relatively lower predictive accuracy than analysis methods with more complex decision boundaries, such as support vector machines. In this study, a decision tree methodology with flexible decision boundaries is proposed. The model based hybrid decision tree improves prediction accuracy by fitting a flexible decision boundary to each node. Furthermore, it reduces a tree size significantly.
Keywords : Data mining, decision tree, hybrid model.