Research on Decision Tree Based on Rough Set

This paper proposes a decision tree generation method based on variable precision rough set theory. The proposed method mainly deals with the uncertain information in the decision tree process and allows a certain degree of noise interference during classification. It mainly summarizes based on entropy and Decision tree construction method based on rough set theory. Two well-known algorithms, ID3 and C4.5, are discussed in terms of entropy. Decision tree based on rough set theory and based on variable precision are introduced in terms of rough set. Decision tree constructed by rough set theory. Then the difference between the method based on rough set theory and basic entropy is discussed. Although the decision tree constructed based on entropy and rough set theory can achieve a good match with the original data set, but it reduces its generalization ability for future data. Compared with the traditional decision tree construction algorithm based on entropy and rough set, the decision tree construction method based on the variable precision rough set theory constructs a simple decision tree structure, which improves the generalization of the decision tree. It also has a certain ability to suppress noise at the same time.