基于三枝决策粗糙集的供应链合作伙伴选择方法

摘要

选择合适的合作伙伴对提升供应链竞争力具有重要的战略意义。选择合作伙伴的常见方法有：线性加权法、数学规划法和层次分析法等，在存在噪声的实际决策环境中，大多数评价和选择方法缺乏对误分类的容错能力。本文根据三枝决策粗糙集理论，提出了一种新的方法来选择合作伙伴。该方法引入了最小风险贝叶斯决策理论，采用定量的概率包含关系来度量对象集合相对于目标概念的隶属度（条件概率），找出最小期望风险的决策，将其作为划分正域、负域和边界域的基本依据。本文给出了该方法的具体步骤，并通过算例对其有效性进行了验证。%It is of great importance to select appropriate partners to promote the competence of supply chains . The common selection approaches includes linear weighting , mathematical planning , AHP , etc . In real decision problems with noise , many of the above evalu-ation and selection approaches are lack of fault tolerance for incorrect classification . This paper proposes a three -way decision approach to the selection of partners based on decision-theoretic rough sets . It introduces Bayesian decision theory for the minimization of risks . It measures the membership , namely conditional probabilities , of the objectives by adopting quantitative probability inclusion relationship . The minimized expected risk provides the principle for the classification of positive , negative and boundary regions . Detailed steps are pro-posed . The validity of the approach is demonstrated by an example .