摘要
文章针对属性值为梯形模糊数的多属性群决策问题,在给出错误和损失相关的概念和设定研究假设前提的基础上,从错误损失的角度提出一种新的决策方法。首先,根据决策者的心理期望特征构建错误函数实现对错误的定量描述,并根据错误值将备选策略划分为可行策略和不可行策略两类;接着,给出属性极限损失函数,进而通过错误值和极限损失值获得损失值。然后,采用TOPSIS法对损失信息进行集结,实现对可行策略的排序与选优。最后,通过一个算例分析不同的心理期望条件对决策分析结果的影响。
Aiming at the multi-attribute group decision-making with attribute value to be trapezoidal fuzzy number, this paper proposes a new decision-making method from the perspective of error loss on the basis of giving the concept of error and loss-related and the premise of setting research hypothesis. Firstly, the paper constructs the error function according to the psychological expectation characteristics of the decision maker to realize the quantitative description of the error, and divides the alternative strategy into feasible strategy and infeasible strategy according to the error value. And then the attribute limit loss function is given, and the loss value obtained by error value and limit loss value. The paper also uses the ToPSIS method to aggregate the loss information to realize the sorting and optimization of feasible strategies. Finally, the paper employs an example to analyze the influence of different psychological expectation conditions on decision analysis results.
作者
黄灏然
蔡肯
贝海坚
Huang Haoran;Cai Ken;Bei Haijian(School of Information Science and Technology,Zhongkai University of Agriculture and Engineering,Guangzhou 510225,China)
出处
《统计与决策》
CSSCI
北大核心
2019年第6期46-50,共5页
Statistics & Decision
基金
教育部人文社会科学研究青年基金项目(15YJC630035)
广东省大学生创新创业训练计划项目(201611347024)
广东省自然科学基金资助项目(2018A030313317)
关键词
错误
损失
梯形模糊数
心理阈值
多属性群决策
error
loss
trapezoidal fuzzy number
psychological threshold
multi-attribute group decision-making
