A Classify Method Research Of Construct Type Of New Country Base On Decision Tree

Data mining is an advanced process, in which we can pick up many trustful, novel, useful and readable patterns from very large amounts of data. Classification is an important part of data mining. Classification now has been widely used in many areas. Many different techniques have been proposed for classification, decision tree classifiers have found the widest application in larger scale data environments.The Fifth Plenary Session of the Sixth Central Committee proposed a great historical mission of constructing new country, which pointed out the direction for "three rural" work of current and future a period. In the process of construction of new country, for reflecting the status of construction of new country, many areas obtain the comprehensive score and place of construction of new country for their areas of analysis by using weighted summation method which is based on comprehensive evaluation index system.Weighted summation method can not obtain the division of the type of a typical representative in the process of construction and it will be difficult to ensure their science and practicality by the division of evaluation index weights. This method is harmful to carry out the action of construction of new country for the governments which adapt to local conditions. Decision tree method of data mining is an inductive learning algorithm based on examples. If the dataset is determined, it will learn to model by depending on data itself completely. The advantages of this algorithm do not rely on domain knowledge and the rules of expression understand easily, the importance of index will be shown clearly.Using data mining technology, a decision tree classify method of construct type of new country was proposed according to evaluation index system and data of construction of new country. This method can classify the instance of construction of new country, so that it not can only obtain the comprehensive score and place in a competition, but also solve the classified problem. By the rules which were obtained from data mining, provide the reference for the revision of evaluation index system. The validity of the given method was suggested by simulations.