Enhancing circular economy project outcomes via molecular fuzzy-based decision support system

Abstract

The most important criteria for increasing the performance of circular economy projects should be identified. Otherwise, companies can make wrong investment decisions that lead to high operational costs. However, the number of studies in which priority analysis is carried out for these factors is not sufficient. This situation creates an essential research gap for this literature. To address this missing gap, this study aims to identify the most critical factors and develop the most effective investment strategies to enhance the performance of circular economy projects. A novel decision-making model is proposed by integrating the Q-learning algorithm, molecular fuzzy sets, cognitive maps, and the Molecular ranking (MORAN) technique. To ensure robustness, a balanced expert dataset is constructed using the Q-learning algorithm, while molecular geometry is considered to reduce complexity and uncertainty in decision-making processes. It is concluded that effective waste management and achieving energy efficiency are the most important indicators. This study contributes to the literature by presenting a novel integrated model that not only enhances decision accuracy but also offers practical strategic guidance for investors seeking to boost the success of circular economy initiatives. The proposed model demonstrates a significant improvement in prioritization accuracy compared to traditional fuzzy decision-making approaches.