Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/1511

Title: Evaluating the performance of cost-based discretization versus entropy- and error-based discretization
Authors: JANSSENS, Davy
WETS, Geert
Issue Date: 2006
Publisher: Elsevier
Citation: COMPUTERS & OPERATIONS RESEARCH, 33(11). p. 3107-3123
Abstract: Discretization is defined as the process that divides continuous numeric values into intervals of discrete categorical values. In this article, the concept of cost-based discretization as a pre-processing step to the induction of a classifier is introduced in order to obtain an optimal multi-interval splitting for each numeric attribute. A transparent description of the method and the steps involved in cost-based discretization are given. The aim of this paper is to present this method and to assess the potential benefits of such an approach. Furthermore, its performance against two other well-known methods, i.e. entropy- and pure error-based discretization is examined. To this end, experiments on 14 data sets, taken from the UCI Repository on Machine Learning were carried out. In order to compare the different methods, the area under the Receiver Operating Characteristic (ROC) graph was used and tested on its level of significance. For most data sets the results show that cost-based discretization achieves satisfactory results when compared to entropy- and error-based discretization.
URI: http://hdl.handle.net/1942/1511
DOI: 10.1016/j.cor.2005.01.022
ISI #: 000237180200004
ISSN: 0305-0548
Category: A1
Type: Journal Contribution
Validation: ecoom, 2007
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Postprint86.87 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.