Tabu Search for Variable Selection in Classification

View Sample PDF

Author(s): Silvia Casado Yusta (Universidad de Burgos, Spain)and Joaquín Pacheco Bonrostro (Instituto de Empresa, Spain)
Copyright: 2009
Pages: 7
Source title: Encyclopedia of Data Warehousing and Mining, Second Edition
Source Author(s)/Editor(s): John Wang (Montclair State University, USA)
DOI: 10.4018/978-1-60566-010-3.ch292

Purchase

View Tabu Search for Variable Selection in Classification on the publisher's website for pricing and purchasing information.

Abstract

Variable selection plays an important role in classification. Before beginning the design of a classification method, when many variables are involved, only those variables that are really required should be selected. There can be many reasons for selecting only a subset of the variables instead of the whole set of candidate variables (Reunanen, 2003): (1) It is cheaper to measure only a reduced set of variables, (2) Prediction accuracy may be improved through the exclusion of redundant and irrelevant variables, (3) The predictor to be built is usually simpler and potentially faster when fewer input variables are used and (4) Knowing which variables are relevant can give insight into the nature of the prediction problem and allows a better understanding of the final classification model. The importance of variables selection before using classification methods is also pointed out in recent works such as Cai et al.(2007) and Rao and Lakshminarayanan (2007). The aim in the classification problem is to classify instances that are characterized by attributes or variables. Based on a set of examples (whose class is known) a set of rules is designed and generalised to classify the set of instances with the greatest precision possible. There are several methodologies for dealing with this problem: Classic Discriminant Analysis, Logistic Regression, Neural Networks, Decision Trees, Instance- Based Learning, etc. Linear Discriminant Analysis and Logistic Regression methods search for linear functions and then use them for classification purposes. They continue to be interesting methodologies. In this work an “ad hoc” new method for variable selection in classification, specifically in discriminant analysis and logistic regression, is analysed. This new method is based on the metaheuristic strategy tabu search and yields better results than the classic methods (stepwise, backward and forward) used by statistical packages such as SPSS or BMDP, as it’s shown below. This method is performed for 2 classes.

The IRMA Community

Research IRM

Tabu Search for Variable Selection in Classification

Purchase

Abstract

Related Content

IRMA Sponsors