@inproceedings{1a3c11d0a89d46c595ba6f9c69775e91,
title = "ConfDTree: Improving decision trees using confidence intervals",
abstract = "Decision trees have three main disadvantages: reduced performance when the training set is small, rigid decision criteria and the fact that a single {"}uncharacteristic{"} attribute might {"}derail{"} the classification process. In this paper we present ConfDTree - a post-processing method which enables decision trees to better classify outlier instances. This method, which can be applied on any decision trees algorithm, uses confidence intervals in order to identify these hard-to-classify instances and proposes alternative routes. The experimental study indicates that the proposed post-processing method consistently and significantly improves the predictive performance of decision trees, particularly for small, imbalanced or multi-class datasets in which an average improvement of 5%-9% in the AUC performance is reported.",
keywords = "Confidence intervals, Decision trees, Imbalanced datasets",
author = "Gilad Katz and Asaf Shabtai and Lior Rokach and Nir Ofek",
year = "2012",
month = dec,
day = "1",
doi = "10.1109/ICDM.2012.19",
language = "English",
isbn = "9780769549057",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
pages = "339--348",
booktitle = "Proceedings - 12th IEEE International Conference on Data Mining, ICDM 2012",
note = "12th IEEE International Conference on Data Mining, ICDM 2012 ; Conference date: 10-12-2012 Through 13-12-2012",
}