The study proposes a novel, convenient and dimensionless model of multi-criteria decision-making (MCDM), hereby referred to as Grey Absolute Decision Analysis (GADA) method. The foundation of the GADA method rests upon the Absolute Grey Relational Analysis (Absolute GRA) model and the system that the method follows to produce GADA Indexes and GADA Weights. The GADA Weights represent the relative weights of decision alternatives under given criteria. The method can handle both positive (“higher the better”) and negative (“lower the better”) criteria simultaneously in its algorithm. The method can deal with problems involving uncertainty and incomplete data. Two practical cases have been presented in the study to demonstrate the feasibility of the method. Furthermore, the GADA Weights obtained for the cases show that these values are comparable to the relative weights obtained through the traditional methods like AHP and SAW thus signifying the feasibility of the method. However, the conventional methods do not consider the mutual association between the judgments of the members of decision-making group (experts’ opinions), a weakness that the proposed method overwhelms. Therefore, the overall ranking obtained from the proposed method is acceptable, especially under the uncertain environment where the nature of mutual association between the judgments is not precise. The key benefit of the method lies in its adaptability to different scales of measurement. Also, it can provide relative weights and rankings of experts, criterion and alternatives. These benefits make the GADA method significant among the class of MCDM methods.

中文翻译：

---

不确定条件下多准则群决策的灰色绝对决策分析（GADA）方法

该研究提出了一种新颖，方便，无量纲的多准则决策模型（MCDM），在此称为灰色绝对决策分析（GADA）方法。GADA方法的基础基于绝对灰色关联分析（Absolute GRA）模型和该方法所遵循的系统来生成GADA指标和GADA权重。GADA权重代表给定标准下决策替代方案的相对权重。该方法在其算法中可以同时处理正面（“越高越好”）和负面（“越低越好”）标准。该方法可以处理涉及不确定性和不完整数据的问题。研究中提出了两个实际案例，以证明该方法的可行性。此外，根据案例获得的GADA权重表明，这些值与通过AHP和SAW等传统方法获得的相对权重相当，从而表明该方法的可行性。但是，传统方法没有考虑决策小组成员的判断之间的相互联系（专家意见），这是该方法难以克服的缺点。因此，从所提出的方法获得的总体排名是可以接受的，尤其是在不确定的环境中，判断之间的相互关联性并不精确。该方法的主要优点在于它对不同测量规模的适应性。而且，它可以提供专家的相对权重和排名，标准和替代方案。