Abstract: Acquiring preferential information of decision maker is the key for multiple attribute decision problem, a lot of these information is hidden in huge amount of historical data. Data mining is a technology for automatic acquiring knowledge. In this paper , by integrating the theory of rough sets, a method of mining decision preferential information is developed. The preferential information inferred from historical data is a set of “if then” decision rule, so it is more understandable.

摘要： 获取决策者的决策偏好信息是多属性决策问题的关键所在，这种偏好信息往往隐藏在大量历史数据中。数据挖掘技术是知识自动获取的一个重要手段。该文基于粗糙集理论提出了一个自动发现决策偏好信息的算法，利用该算法挖掘出的偏好信息采用if …then 规则的形式，因此更容易被决策者所理解。

关键词: 数据挖掘, 多属性决策, 粗糙集

CLC Number: 

• TP311.52