Artificial Intelligence and MCDA in Circular Economy: Governance Strategies and Optimization for Reverse Supply Chains of Solid Waste

Abstract

The integration of multi-criteria decision analysis (MCDA) and Artificial Intelligence (AI) is revolutionizing the governance of reverse supply chains for solid waste (RSCSW) within a circular economy framework. However, the existing literature lacks a systematic assessment of the effectiveness of these methods compared to traditional waste management practices. This study conducts a systematic literature review (SLR), following PRISMA guidelines and the P.I.C.O. framework, to investigate how MCDA and AI can optimize governance, operational efficiency, and the sustainability of RSCSW. After collecting 1139 articles, 22 were selected and used for analysis. The results indicate that hybrid MCDA-AI models, employing techniques, such as TOPSIS, AHP, neural networks, and genetic algorithms, enhance decision-making automation, reduce costs, and improve waste traceability. Nevertheless, regulatory barriers and technological challenges still hinder large-scale adoption. This study proposes an innovative framework to address these gaps and drive evidence-based public policies. The findings provide guidelines for policymakers and managers, contributing to the Sustainable Development Goals (SDGs) agenda and advancements in circular economy governance.

Keywords

• multi-criteria decision analysis
• artificial intelligence
• reverse supply chains
• circular economy
• solid waste management
• sustainability