考虑决策者损失规避的异质信息多属性变权决策方法

现实中存在大量异质信息（或数据）和需要考虑权重随属性值变化的多属性决策问题。针对这类异质信息多属性决策问题，本文提出了一种基于前景理论的变权综合求解方法。首先，构建了异质信息的统一距离计算公式，进而计算各个决策方案的相对贴近度；然后，提出基于不同类型效用函数的变权向量构造方法；其次，以初始权重为参考点，计算变权向量相对于参考点的益损决策矩阵，进而计算考虑决策者权重损失和收益的风险态度的各个决策方案的前景综合值，据此确定方案优劣排序和最优方案。通过数值例子的计算分析说明，文中所提决策模型与方法具有较好的有效性和合理性，可为解决复杂情景的决策问题提供理论依据与方法支持。

Heterogeneous Multi-attribute Variable Weight Decision Making Method Considering Decision Maker's Loss Aversion

There are many multi-attribute decision making problems with heterogeneous information or data, which also needs to consider that the weights change with the attributes values. Aiming at the heterogeneous information multi-attribute decision making, a variable weight decision making method is proposed based on prospect theory. Firstly, the unified distance formula of heterogeneous information is built, furthermore, the relative closeness of alternatives are computed. Secondly, variable weight vector based on different types of utility functions are obtained. In the next place, the initial weight is chosen as the reference point, the variable weight vector is transformed into the decision matrix of gains or losses relative to the reference point. Furthermore, considering the decision maker's different risk attitudes toward gains and losses, the comprehensive prospect value of each alternative is calculated based on prospect theory, a ranking of alternatives is determined by the comprehensive prospect value. Finally, an illustrative example shows the effectiveness and validity of the proposed model and approach, which can provide theoretical basis and method support for solving the complex scenarios decision problem.