A hybrid decision tree classifier

Article type: Research Article

Authors: Kotsiantis, Sotiris

Affiliations: Educational Software Development Laboratory, Department of Mathematics, University of Patras, Rio, Greece

Note: [] Corresponding author. Sotiris Kotsiantis, Educational Software Development Laboratory, Department of Mathematics, University of Patras, P.A. Box: 1399, Rio 26 504, Greece. Tel: +30 2610 996769; Fax: +30 2610 997313; E-mail: sotos@math.upatras.gr

Abstract: Decision tree techniques have been widely used to build classification models. In this study, we attempted to increase the prediction accuracy of a decision tree model by integrating local application of Naive Bayes classifier. We performed a large-scale comparison with other state-of-the-art algorithms on 30 standard benchmark datasets and the proposed method gave statistical better accuracy in some cases.

Keywords: Decision tree, classification tree, Naive Bayes, hybrid classifier

DOI: 10.3233/IFS-120741

Journal: Journal of Intelligent & Fuzzy Systems, vol. 26, no. 1, pp. 327-336, 2014