AI-Driven ESG Supplier Evaluation Frameworks for Sustainable Global Procurement Networks

Abstract

The increasing emphasis on sustainable procurement has intensified the need for intelligent supplier evaluation systems capable of integrating Environmental, Social, and Governance (ESG) considerations into global sourcing decisions. Traditional supplier assessment approaches frequently rely on static scorecards and subjective evaluation procedures, resulting in inconsistent sustainability assessment and limited responsiveness to evolving supply chain risks. This study presents a conceptual AI-driven ESG supplier evaluation framework designed to support sustainable procurement decision-making within global procurement networks. The framework integrates machine learning, predictive analytics, Natural Language Processing (NLP), and explainable artificial intelligence into a unified procurement intelligence architecture for supplier sustainability assessment and ESG risk evaluation. Environmental indicators such as carbon emissions and resource efficiency, social indicators including labor compliance and employee welfare, and governance indicators such as transparency and ethical sourcing are incorporated into a multidimensional supplier evaluation structure. The study adopts a conceptual and analytical framework-development approach grounded in existing literature on sustainable procurement, ESG governance, and intelligent supply chain systems. Rather than presenting empirical model experimentation, the study proposes a structured analytical architecture intended to guide future implementation and empirical validation efforts. The framework contributes to the growing literature on AI-enabled sustainable procurement by providing an integrated conceptual foundation for intelligent supplier evaluation, sustainability monitoring, and procurement governance within complex global supply chain environments.