一种改进的决策树学习算法  

An Improved Decision Tree Learning Algorithm

作　　者：李瑞[1] 魏现梅[1] 黄明[1] 梁旭[1] 

机构地区：[1]大连交通大学软件学院,大连116028

出　　处：《科学技术与工程》2009年第20期6038-6041,共4页Science Technology and Engineering

基　　金：辽宁省自然科学基金(20072161)资助

摘　　要：为提高C4.5算法的准确率引进一个平衡度系数,其大小由决策者依靠先验知识或领域知识确定,在特定环境下人工协调了各属性信息增益率,用改进后的算法构造出的决策树进行分类更为准确、合理。并通过实例分析对改进前后的算法进行了比较,证明改进算法的有效性。A balanced coefficient to improve the veracity of C4. 5 algorithm is introduced. It can be fixed by decision maker according to priori intellectual and domain intellectual. It harmonized the information gain-ratio of each attributes artificially in specific environment. The classification is more veracious and rational by the decision tree made from the improved algorithm. And compared the improved algorithm to C4. 5 algorithm by analyzing examples, to prove the efficiency of the improved algorithm.

关 键 词：数据分类 决策树 C4.5算法 平衡度系数 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]