基于决策树算法的信息系统数据挖掘研究

为了提高数据挖掘准确性和效率,文中提出了基于决策树算法的信息系统数据挖掘方法。以C4.5决策树算法计算属性的信息增益率和属性值的信息熵为基础,提出基于余弦相似度改进的C4.5决策树算法,若任意两个属性值的信息熵之差在阈值范围内,通过计算其余弦相似度合并在阈值范围内的属性值,并重新计算合并后属性的信息增益率,实现信息系统数据挖掘。实验结果显示:所提方法对不同数据集的分类精度均高于95%,数据挖掘效率高。

Research on information system data mining based on decision tree algorithm

In order to improve the accuracy and efficiency of data mining,a data mining method of information system based on decision tree algorithm is proposed.On the basis of information gain rate based on C4.5 decision tree algorithm attributes and the information entropy of attribute values,an improved C4.5 decision tree algorithm based on cosine similarity is proposed.If the difference of information entropy between any two attribute values is within the threshold range,the information system is realized by calculating the cosine similarity of the attribute values merged within the threshold range and recalculating the information gain rate of the merged attributes.The experiment results show that the classification accuracy of the proposed method for different data sets is higher than 95%,and the data mining efficiency is high.