A machine learning framework for classifying customer advocacy in sustainable supply chains

Abstract

Sustainable supply chain management plays a pivotal role in shaping corporate reputation and enhancing customer loyalty in the contemporary market. This study uniquely integrates regional, demographic, and psychographic data with advanced machine learning methodologies, including clustering, decision trees, and association rule mining, to classify and predict customer advocacy based on Environmental, Social, and Governance (ESG) performance indicators and supply chain risk management. Unlike previous research, the analysis explicitly segments customers by their distinct ESG trust perceptions and advocacy behaviours, providing nuanced insights into how varying demographic and regional characteristics influence customer support for sustainable practices. Results reveal that customer advocacy patterns significantly differ across segments, particularly highlighting groups with strong environmental concerns and positive evaluations of governance practices. The study’s comprehensive approach not only advances theoretical understanding by integrating diverse customer attributes but also delivers precise, actionable recommendations for supply chain managers to foster targeted and effective sustainable initiatives.