Optimizing parametric insurance for renewable energy investments: Integrating fuzzy decision-making and artificial intelligence techniques

Small-scale solar panel investments have significant risks because of market fluctuations. However, traditional insurance models often lead to inadequate coverage. This situation has a negative impact on profitability of the projects. To satisfy this situation, this study evaluates the effectiveness of parametric insurance by identifying optimal factors in this process. The research applies an artificial intelligence-based sine trigonometric Pythagorean fuzzy (STPF) entropy technique and CRiteria Importance Through Intercriteria Correlation (CRITIC) methodology to determine the significance of criteria. In addition, geometric mean of similarity ratio to optimal solution (RATGOS) approach is employed to rank risk factors. The main contribution of this paper is that integrating the Artificial Intelligence (AI) approach into fuzzy decision-making techniques increases both the quality and originality of the proposed model. With the help of this issue, decision matrix can be constructed via AI technique so that more realistic and appropriate findings can be identified. Findings indicate that cost is the most influential factor (weight: 0.1059), followed by trigger (weight: 0.0632), policy (weight: 0.0629), and adoptability (weight: 0.0587). On the other side, based on the ranking results, price is the most essential alternative for making parametric insurance regarding small scale solar panel investments. Therefore, policymakers and insurers should focus on cost-optimized coverage models to prioritize essential risk factors while avoiding unnecessary over-insurance.