The Study Of Decision Tree Classification Algorithm And Its Application

With the development of information technology,data mining technology has been widely used.Classification problem is an important issue in data mining,classification algorithm is one of the commonly used methods in data mining and decision tree classification algorithm is studied in this paper,and the main contents are as follows:(1)Based on the analysis and comparison of several kinds of typical decision tree algorithm,summarizes the characteristics of each algorithm,established an improved decision tree classification algorithm.The algorithm for those who are not easy to distinguish between the properties of the calculated its decision-making support with a new theory as the basis of attribute selection,to redefine the algorithm process,thus established the effective decision tree.(2)Using UCI data sets,the database will be established in this paper,the decision tree classification algorithm and ID3 algorithm experimental comparison,obtained the good effect.At the same time,in order to ? avoid more as the test attribute value problem,this paper also introduces the degree of interest,effectively avoid the problem of multi-valued bias.(3)Collected data of xi'an part of students in his grade,family income,whether the graduating class and grades as condition attributes,whether in the extracurricular classes as decision attribute,using the model established in this paper,the decision tree classification algorithm for empirical research,a better classification results were obtained.