A New Method for Constructing Decision Tree Based on Rough Set Theory

Decision tree induction algorithms have been used for classification in a wide range of application domains. In the process of constructing a tree, the criteria of selecting test attributes will influence the classification ability of the tree. The paper present a new method of constructing decision trees based on rough set that uses a core attribute and a discernibility matrix to select the attribute with the maximal contribution to classification. The result of a example shows that our approach is a better way to select nodes for construction decision trees.