Supply Chain Research

Abstract Industry 4.0 is revolutionizing manufacturing by integrating advanced technologies like IoT, AI, and robotics to enable higher levels of automation, real-time insights, and operational agility. This transformation offers substantial opportunities but also poses challenges in achieving manufacturing excellence through enhanced quality, efficiency, responsiveness, and sustainability. This paper reviews the key technological enablers, strategic priorities, and organizational changes driving smart, resilient, and sustainable manufacturing in the Industry 4.0 era. It proposes an integrated methodology that combines digital technologies—including IoT, AI, digital twins, and collaborative robotics—with a human-centered approach. The methodology organizes Industry 4.0 strategies into five domains: Quality & Innovation, Asset & Operations, Supply Chain & Logistics, Safety & Sustainability, and People & Customer Engagement, demonstrating how these areas improve efficiency, asset management, supply chain transparency, safety, and workforce capabilities to enhance agility and competitiveness. Central to this is the use of cyber-physical systems for real-time data exchange, transforming factories into adaptive smart ecosystems. Challenges such as legacy system integration, cybersecurity risks, skill gaps, and resistance to change are addressed through phased adoption, robust security, continuous workforce development, pilot projects, and strong leadership. The framework integrates Lean, Six Sigma, and Agile methods with real-time analytics, an enhanced DMAIC cycle, and adaptive KPIs to drive continuous improvement and operational excellence. By aligning technology, processes, people, and sustainability, it supports building agile, resilient, and sustainable production systems that secure long-term competitive advantage. This conceptual framework presents a practical roadmap for Industry 4.0 transformation and will be further refined and validated through future case studies and pilot projects to facilitate wider adoption and ongoing improvement.

Abstract To forecast future purchases across several product categories—including fresh milk, groceries, frozen foods, detergents, paper, and delicatessen—this study looks at the purchasing patterns of wholesale clients using machine learning models. Support Vector Machines, Generalised Linear Models, and Linear Regression were among the predictive models used. RMSE, MAPE, and R² metrics were used to assess each model's performance and ascertain its correctness. The results show that when it came to forecasting consumer purchases, GLM performed better than other models, including LR, SVM, RT, and ER.