A multi-objective optimization and machine learning framework for smart supply chain design with IoT and blockchain

Addressing the escalating complexity and demands for resilience, sustainability, and real-time visibility in modern supply chains, this study develops and validates a novel hybrid engineering framework. This framework synergistically integrates machine learning and multi-objective optimization to design and manage smart supply chains leveraging Internet of Things (IoT) and blockchain technologies. A bi-objective mathematical model is formulated to concurrently minimize total operational costs and delivery times, while inherently supporting enhanced traceability, transparency, and environmental performance. To overcome the computational challenges posed by large-scale problem instances, a Multi-Objective Gray Wolf Optimizer (MOGWO) is engineered and applied. The framework further incorporates machine learning for precise demand forecasting and operational parameter estimation, utilizing real-time RFID and sensor data to significantly improve decision accuracy. Comprehensive computational experiments demonstrate that the proposed model achieves substantial performance improvements, reducing total costs by up to 18.7 % and delivery times by 22.4 % compared to traditional supply chain models without IoT and blockchain integration. Furthermore, blockchain integration demonstrably enhances data transparency and trust across the supply network. The results underscore the framework's efficacy in generating diverse Pareto-optimal solutions and highlight the critical engineering value of digital transformation in fostering intelligent, resilient, and sustainable supply chain systems.