An Improved ID3 Decision Tree Algorithm Based on Attribute Weighted

Abstract

ID3 decision tree algorithm uses information gain selection splitting attribute tend to choose the more property values, and the number of attribute values can not be used to measure the attribute importance, in view of the above problems, a new method is proposed for attribute weighting, the idea of simulation conditional probability, calculation of the close contact between the attributes and the decision attributes, as the attribute weights and combination with attribute information gain to selection splitting attribute, improve the accuracy of decision results.