Improving Linguistic Pairwise Comparison Consistency via Linguistic Discrete Regions

Linguistic pairwise comparison matrices are widely used in decision-making procedures. However, the matrices often give conflicting results when there are multiple criteria under consideration. Despite intensive research, achieving consistency of such matrices remains a daunting task. In this paper, a novel approach based on linguistic discrete region is proposed to address the challenge. Unlike existing methods that require a single value for each comparison, our approach allows a comparison to be expressed by a discrete region with multiple linguistic terms. Such front-end gives users more freedom to express their opinions. In the back-end, we propose an iterative searching algorithm that is able to achieve approximate optimal consistency for the comparison matrices with discrete region values. The final results are single-value matrices that not only guarantee approximate optimal consistency but comply with evaluators' intentions a well, as our approach does not modify any linguistic values like many existing methods. We have conducted extensive evaluations, and our empirical study confirms that the linguistic discrete region-based approach significantly improves the consistency of linguistic pairwise comparison matrices.