Robust Optimization of Pharmaceutical Supply Chain Through ML Algorithms Fostering Resilience and Reducing Wastages

Abstract

This study examines the application of machine learning (ML) algorithms within pharmaceutical supply chains, emphasizing their role in enhancing resilience and minimizing waste. A structured questionnaire was distributed to seventy professionals representing supply chain management, logistics, procurement, regulatory affairs, and quality assurance. Responses were analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM). The results demonstrate that domain-specific ML algorithms substantially improve forecasting accuracy, strengthen regulatory compliance, and optimize inventory management compared with conventional methods. Forecasting accuracy and stakeholder readiness achieved high reliability (Cronbach’s Alpha: 0.86 each), whereas adoption barriers, largely reflecting limited organizational confidence in digital transformation, showed only moderate reliability (Cronbach’s Alpha: 0.57). Despite the relatively small sample, the findings underscore the transformative potential of hybrid AI-classical models, integration with blockchain and IoT sensors, and federated learning approaches for pharmaceutical supply chains. The study proposes a novel framework that balances predictive precision with regulatory feasibility, offering actionable insights to support resilient and globally scalable pharmaceutical logistics.