Research on the missing attribute value data-oriented for decision tree

In the existing multiple choice methods of decision tree´ test attributes, can´t see such report as” Let missing data processing integrated in the selection process of test attributes”, however, the existing process methods of missing attribute value data can draw into bias in different degrees, base on this, propose an information gain rate base on combination entropy as the decision tree´s testing attributes selection criteria, which can eliminate missing value arrtibutes´ infulence on testing attributes selection, and be implemented on WEKA. The computational complexity of the MultiInfo Tree is better than that of C4.5.