An Improved ID3 Classification Algorithm Based On Correlation Function and Weighted Attribute

摘要: ID3 decision tree algorithm is a supervised learning model based on calculating the information gain to select best splitting attribute, which main factor construct tree. The process of takes into consideration only current condition attribute and other attributes cannot be used measure importance. Because above problem, an improved connection between conditions attributes. An experiment presented compare our with traditional algorithm. Experiment results show that provides less number leaves higher predictive accuracy.