Verifying cuts as a tool for improving a classifier based on a decision tree

This article is a continuation of previous work, in which a new method of decision tree construction was presented. That method is based on the use of so-called verifying cuts, which can provide knowledge obtained from the attributes frequently eliminated when greedy methods of the choice of singleton best cuts are applied. Till now only one strategy of choosing verifying cuts was examined. It exploits a measure based on a number of pairs of objects discerned by a chosen cut. In this paper, we examine two additional measures used for determining the best verifying cuts. They are based on Gini's Index and Entropy. The paper includes the results of experiments that have been performed on data obtained from biomedical database and machine learning repositories.