A Multi-Criteria Decision-Making Technique Based on Generalized Bipolar Fuzzy Prioritized Operators and Their Application in Supply Chain Management

The evaluation and assessment of AI-driven models for supply chain management require complex decision-making frameworks that can cope with uncertainty, indecision, and conflicting expert opinions. The expressiveness of traditional fuzzy decision-making models is limited and is not able to represent both positive and negative sides of the criteria. In addition, existing generalized aggregation operators (AOs) rely on arbitrary weights of criteria that introduce subjectivity and reduce the accuracy of the findings. This paper addresses these shortcomings by suggesting a new multi-criteria decision-making (MCDM) method based on generalized bipolar fuzzy prioritized operators (G-BFPR). We propose four new operators, namely, generalized bipolar fuzzy prioritized average (G-BFPRA), generalized bipolar fuzzy prioritized weighted average (G-BFPRWA), generalized bipolar fuzzy prioritized geometric (GBFPRG), and generalized bipolar fuzzy prioritized weighted geometric (G-BFPRWG) operators. This framework, in a systematic manner, computes weights using priority relations, eliminating subjectivity and reflecting on positive and negative preferences in uncertain settings. Our approach provides a context-specific, balanced assessment mechanism of AI-based supply chain models, which is demonstrated by a case study that validates the superiority of our approach to the current theories. The proposed bipolar fuzzy MCDM method offers a holistic solution to the ranking of optimization techniques in supply chain management, which enhances operational performance, minimizes costs, and enhances sustainability. Furthermore, the needs and benefits of the proposed work are disclosed in this article, as it includes a comparative analysis.