多目标决策研究:基于藤copula和SMAA方法  

Using copula method with SMAA in decision-making analysis

作　　者：邓维 叶五一 杨锋 DENG Wei;YE Wuyi;YANG Feng(Department of Management Science, School of Management, University of Science and Technology of China,Hefei 230026, China)

机构地区：[1]中国科学技术大学管理学院管理科学系,合肥230026

出　　处：《中国科学院大学学报（中英文）》2022年第4期449-462,共14页Journal of University of Chinese Academy of Sciences

基　　金：国家自然科学基金面上项目(71973133)资助。

摘　　要：运用藤copula构造模型分析多组决策变量之间的相互依赖以及不确定性,创新地将SMAA方法与copula相依性分析结合在一起,得到更优良更有效的随机多准则可接受性分析方法。介绍基本的藤copula建模分析和SMAA的方法,展示两种方法结合使用的完整步骤,并在数据模拟分析实践中,通过对比新方法与原有的SMAA方法,得到在不同相互依赖结构下的表现结果,证明了新方法更普适、更准确的优点。Stochastic multi-criteria acceptability analysis(SMAA)is a series of methods for multi-criteria decision making.It is used to give decision opinions on the problem of uncertain or missing preferences of decision makers,the uncertainty of decision variables and incomplete or missing preference information can be represented by probability distribution.This method improves the past methods by considering inversely what specific parameters each decision outcome is determined by.However,the existing SMAA methods does not take into account the impact of the interdependence between these variables on the analysis results,or simply using a simple model such as a Gaussian distribution to describe these interdependencies,so that the analysis results do not have sufficient scientific basis.In order to fix this fault,this paper create an innovation by combining copula dependency analysis with stochastic multi-criteria acceptability analysis method,and uses vine copula modeling method to describe the uncertainty of decision variables and their interdependence,making the SMAA method complete and more effective.This paper introduces the basic methods of SMAA and vine copula separately,and gives the specific steps of combining the two methods.In simulation experiments,a comparative analysis is conducted between the original SMAA method and the method given in the paper to show their advantages and disadvantages under different dependency structures.

关 键 词：决策分析 随机多标准可接受度分析 相依分析 连接函数 藤结构 

分 类 号：C934[经济管理—管理学]