基于累积前景理论的信息不完全的风险型多准则决策方法  

Multi-attribute Decision Making Method under Risk Based on Cumulative Prospect Theory with Incomplete Information

作　　者：王雪青[1] 唐瑭[1] 

机构地区：[1]天津大学管理与经济学部,天津300072

出　　处：《模糊系统与数学》2015年第3期137-144,共8页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(71231006)

摘　　要：针对属性值为梯形模糊数、准则权重不确定的风险型多准则决策问题,提出一种基于累积前景理论的决策方法。该方法定义了梯形模糊数的排序方法以及距离测度公式;以正、负理想点方案作为参考点计算各状态下的前景价值;通过权重函数将动态前景价值转化为静态前景矩阵。在此基础上求解基于矩估计理论的最优组合赋权模型得到各准则的权重。根据各方案的综合前景值对方案进行排序。最后,通过算例分析以及方法比较结果验证了该方法的合理性,表明该方法符合风险偏好以及风险感知下决策者的风险决策行为。With respect to the decision-making problems under risk with trapezoidal fuzzy number and unknown attributes＇ weights, a multi-attribute decision making method based on cumulative prospect theory is proposed. To begin with, the ranking method and the distance measure for trapezoidal fuzzy number are defined, respectively. Dynamic prospect values are calculated by using the positive ideal solution and the negative ideal solution as the preference point. Then the static prospect values are aggregated by dynamic prospect values through the weight function. Furthermore, the weighted prospect value of alternative is acquired with the attributes＇ weights under condition that every attributes＇ weight is obtained from a programming model based on the moment-matching method, which all the alternatives are sorted according to. Finally, numerical result illustrates the rationality of this approach, and indicates that the proposed method is conformed to the risk decision-making behavior with the risk appetite and risk perception.

关 键 词：前景理论 多准则决策 梯形模糊数 逼近理想点法 组合赋权 

分 类 号：C934[经济管理—管理学]