Human–computer collaboration in decision-making: A dynamic multi-facet fuzzy optimization model for sustainable energy investments

There is still no consensus in the literature on how renewable energy investments aligned with the Sustainable Development Goals (SDGs) should be prioritized. This lack of clarity creates uncertainty for policymakers and investors and weakens the long-term sustainability perspective in decision-making. To address this gap, this study develops a novel Dynamic Multi-Facet Fuzzy Set (DMFFS)–based decision-making model to identify the most appropriate SDG-oriented renewable energy investment alternatives. The DMFFS represents a new methodological formulation that introduces a dynamic, parameter-driven adaptation mechanism, allowing membership functions to flexibly adjust under multiple decision scenarios to manage uncertainty more effectively. The proposed framework integrates expert evaluations with parameter-driven artificial assessments, calculates criteria weights through dynamic influence propagation with entropy optimization, and ranks alternatives using the weighted aggregated sum product assessment (WASPAS) method. The findings reveal that continuous learning is the most critical factor for improving sustainability performance, while health and well-being are also significant. Among renewable energy alternatives, geothermal and solar energy emerge as the most suitable options. These results provide practical guidance for policymakers and managers in designing effective, SDG-compatible investment strategies that enhance both environmental and organizational sustainability.