A Machine Learning–Based Multi-Criteria Decision-Making Model for Prioritizing Climate Change Policy Strategies under Spherical Fuzzy Environment

The objective of this study is to identify the most prioritized policy strategies that can be implemented to combat climate change, thereby filling the gap in the literature and providing policymakers with a scientifically based roadmap. The proposed model utilizes the opinions of five experts. A machine learning-based method calculates importance weights based on the experts' demographic characteristics. The criteria importance through intercriteria correlation (CRITIC) is used to determine the criteria weights, and the weighted aggregated sum-product assessment (WASPAS) is considered to rank policy alternatives. Furthermore, spherical fuzzy sets are integrated into the model to more effectively manage uncertainties. The study contributes to the literature by proposing a unique decision-making model where expert weights are objectively calculated using machine learning, CRITIC and WASPAS methods are applied in an integrated manner, and uncertainty is managed more flexibly and reliably through spherical fuzzy sets. This model offers an innovative solution to the long-discussed problem of "assuming equal expert weights" in the literature and provides a more robust methodological framework for policy environments with high uncertainty. Research findings indicate that the most critical criteria are technological feasibility and economic feasibility. Moreover, carbon taxes and renewable energy incentives are the most optimal policy strategies.