摘要
在数据挖掘的研究与应用中,学者们提出了一系列的分类模型,如贝叶斯模型、决策树模型、人工神经网络模型等,其中决策树模型由于其简洁、高效、易于理解和使用,得到广泛的应用。然而,关于决策树评分函数的研究尚未取得令人满意的结果。分析了目前流行的一些评价指标,研究了其适用范围和局限,并对评分函数做了必要的补充和完善,试图建立一套相对科学合理的评价体系。
In the study and use of data mining technologies, some scholars have put forward a series of classification models, such as Bayesian classifier, decision tree, neural network and etc. Among these models, decision tree is widely used due to its simplicity, high-efficiency and easy-usage. But satisfactory progress has not made in the score functions of decision tree models. This paper analyzed some popular assessment methods and studied their applicable scopes and limits. Further more the author perfected the score functions of decision tree models to set up a logical assessment system.
出处
《管理学报》
2005年第S2期166-168,共3页
Chinese Journal of Management
关键词
决策树模型
数据挖掘
评分函数
decision tree model
data mining
score function
