A Case based Practical Approach for Novel Data Transformation to Enhance Accuracy of Decision Tree Ensembles

Abstract

Abstract
If we talk about any real world situation then we can see that all the situations dramatically changes as the time passes. If we say this statement in some technical form, concepts changes gradually. This situation is called as Concept Drift that is the core of any approach. Until we cannot get the accurate output for a given input parameter, the concepts will concurrently change. To overcome this situation we use a programmable approach that is Classifier Ensembles in which we combine several outputs and form a single output from several. Other thing we get about is Decision Tree that is a very popular ensemble method because Decision Trees are unstable classifiers whose output undergoes significant changes. Data transformation is a process by which the problem representation is changed and we have to manipulate the problems by using some useful techniques. This paper firstly focuses on the popular ensembles methods, the overview of decision tree and uses the concept of classifier ensemble with respect to decision trees. There are mainly two problems associated with data transformation and we have different approaches to resolve these problems. In this paper we consider a single novel transformation method to resolve these problems.

Keywords: Ensemble, decision trees, data, transformation method