Sustainable investment decision-making is challenged by inconsistencies in Environmental, Social, and Governance (ESG) ratings. By applying a quantitative panel data approach to 60 firms sourced from Refinitiv over a period of five years (2019–2023), the study refines traditional ESG scoring techniques by applying fuzzy logic techniques, specifically the Linguistic Ordered Weighted Geometric Aggregation (LOWGA) operator and fuzzy TOPSIS. The enhanced model captures quantitative and qualitative aspects of sustainability performance in order to improve comparability and transparency between companies. An empirical analysis reveals that, although ESG adoption initially adversely affects profitability, as measured by Return on Assets (ROA) and Return on Equity (ROE), over time firms can achieve operational stability and improved efficiency. AI-enhanced ESG analytics have the potential to inform investment strategies, risk management, and policy harmonization, according to the study. The proposed methodology provides a robust framework for academics and practitioners, paving the way for more resilient sustainability-based investment practices.