Intelligent Expert Systems Using Molecular Fuzzy Genetic Algorithms and Multi-Objective Particle Swarm Optimization for Circular-Oriented Project Investments

Circular-oriented project investments promote sustainable growth by enhancing resource efficiency and minimizing waste. There is a significant gap in the literature to identify key variables that influence the performance of these investments. This gap can cause inappropriate decisions by investors and policymakers, as well as inefficient resource utilization by businesses. To address this missing gap, this study aims to identify the key indicators influencing circular-oriented project investments by introducing a novel decision-making model. The proposed model integrates the information gain technique for project prioritization, Q-learning for expert evaluation, genetic algorithms for criteria weighting, and swarm optimization for alternative ranking. The main contribution of this study is that molecular fuzzy sets are considered by combining molecular geometry and fuzzy logic. These sets offer a more advanced uncertainty modeling capability than traditional fuzzy sets. The application of genetic algorithms in criteria weighting provides a significant contribution to the literature. By making a global optimization, more appropriate calculations can be performed for criteria weighting. The findings denote that emission reduction and financial performance are the most crucial criteria for the performance improvements of these projects. Moreover, waste-to-energy plants and urban mining initiatives are found as the most significant project alternatives.