مشخصات پژوهش

Purpose The rapid evolution of Industry 4.0 (I 4.0) technologies has transformed supply chain (SC) operations, creating a need to redefine key performance indicators (KPIs) in quality management (QM). Addressing the lack of data-driven frameworks for evaluating Supply Chain Quality Management 4.0 (SCQM 4.0), this study identifies and prioritizes the most influential KPIs through the integration of machine learning (ML) techniques and managerial insights. Design/methodology/approach A mixed-method approach was employed. First, a systematic literature review (SLR) and expert interviews were conducted to identify relevant indicators. Second, a structured survey of 331 professionals from diverse industries was analyzed using seven supervised ML algorithms (SVM, KNN, RF, LDA, DT, RUSBoost and SVM 1-vs-All). The Random Forest (RF) algorithm achieved the highest accuracy and was applied to determine the final prioritization of KPIs. Findings The results indicate that indicators of digital innovation, supplier responsiveness, customer and supplier involvement, supplier resilience and customer satisfaction are the most critical drivers of SCQM 4.0 performance. The RF algorithm demonstrated superior predictive capability in modeling the relationships among multi-level indicators across upstream, internal and downstream dimensions. Practical implications The findings provide managers with a structured, data-driven framework to enhance quality integration and performance within digitalized supply chains. Implementing ML-based analytics supports proactive KPI monitoring, evidence-based decision-making and continuous quality improvement under I 4.0 conditions. Originality/value This study offers one of the first empirical, ML-based frameworks for assessing SCQM 4.0. It bridges conceptual and operational perspectives by integrating data analytics with managerial expertise, thereby extending Quality 4.0 (Q 4.0) and SC 4.0 literature through a multi-level, performance-oriented lens.