关键词: 决策树 Chi2的变形 离散化 筛选

Abstract:

The simplification of training dataset representation and the generation of decision trees are two critical phases in decision tree induction. On the  condition of bringing the inconsistency rate under a threshold, reducing the attribute number and the different value number of each attribute assures t he feasibility and effectiveness of the decision tree learning method. In this paper, a variation of the Chi2 algorithm is proposed to perform attribute  discretization and selection. The decision tree generated in the further steps offers a good classification accuracy. Our experiment is based on a data  set donated by an insurance company from the real world.

Key words: （decision tree, variation of Chi2, discretization, selection）