摘要
经典决策树算法不能处理树构建和分类过程中的不确定数据,针对这一局限,提出基于概率分布的方法,把决策树分类技术扩展到含有不确定数据的环境中。然后,针对软件外包评价中普遍存在着不确定数据,应用决策树分类方法,对软件外包公司进行客观评价。实验表明,本文提出的基于不确定数据的决策树分类算法能够实现对软件外包评价的定量研究。
Classic decision tree algorithm is unfit to cope with uncertain data pervaded at both the construction and classification phase. In order to overcome these limitations, distribution-based classification algorithm is proposed. This algorithm extends the decision tree technique to an uncertain environment and then applies this decision tree classification algorithm to uncertain data among software outsourcing evaluate domain. The result would be proved efficiently and good performance.
出处
《天津职业技术师范大学学报》
2011年第3期50-53,共4页
Journal of Tianjin University of Technology and Education
基金
天津市应用基础及前沿技术研究计划(10JCYBJC07500)
关键词
不确定数据
决策树算法
软件外包
价值评价
uncertain data
decision tree algorithm
software outsourcing
value evaluate
