大型群组多属性决策Bayes概率修正法

发布时间：2018-05-05 20:47

本文选题：Pareto有效解 + 优势集　；参考：《控制与决策》2013年07期

【摘要】：针对大型群组多属性决策问题,给出了备选对象的优势集和Pareto有效率,并讨论了二者的性质.证明并指出了只有备选对象为Pareto解时,其Pareto有效率才可能不为0.将Pareto备选对象的Pareto有效率作为其"最优决策"的先验概率分布,然后利用Bayes公式和群组专家们决策的后验概率对其加以修正,即可得到"最优决策"概率最大的备选对象.该方法在充分利用专家组决策信息的前提下避免了寻找一个主观集结规则的决策问题,不需要集结出一个权重结果,从而减少了决策过程中主观因素的影响,并且当将每位专家的决策看成一个独立的随机实验时,理论上专家人数越多,决策结果越精确.最后以一个算例说明了所提出方法的有效性.
[Abstract]:For large group multi-attribute decision making problem, the superiority set and Pareto efficiency of alternative objects are given, and their properties are discussed. It is proved and pointed out that when the alternative object is Pareto solution, its Pareto efficiency can not be 0. The Pareto efficiency of the Pareto candidate is regarded as the prior probability distribution of its "optimal decision". Then the Bayes formula and the posteriori probability of the group expert decision are used to modify it, and the candidate with the highest probability of the "optimal decision" can be obtained. Under the premise of making full use of the decision information of the expert group, the method avoids the problem of finding a subjective aggregation rule, and does not need to assemble a weight result, thus reducing the influence of subjective factors in the decision-making process. When the decision of each expert is regarded as an independent random experiment, the more the number of experts is, the more accurate the decision results are. Finally, an example is given to illustrate the effectiveness of the proposed method.
【作者单位】：中南大学商学院;
【基金】：国家自然科学基金创新群体项目(70921001);国家自然科学基金面上项目(71072078,70971139);国家自然科学基金青年项目(71103203) 教育部人文社会科学基金项目(09YJC790260) 中南大学人文社科杰出青年人才基金项目(2011RWSK008) 中南大学2011年青年教师助推专项基金项目(2011QNZT237)
【分类号】：C934

【参考文献】