Modelling of Network Supply Chain through Dynamic Bayesian Networks
Alba Fernández, Marcos López, Elena Ruiz · Optimizations in Applied Machine Learning · 2025
In the era of globalized trade, the management of network supply chains is crucial for the efficiency and competitiveness of business operations. However, existing research has identified significant gaps in modeling and analyzing the dynamic behavior of network supply chains, leading to suboptimal decision-making processes. This paper addresses this challenge by proposing a novel approach utilizing Dynamic Bayesian Networks to model the complex interactions and uncertainties within network supply chains. By integrating probabilistic graphical modeling techniques with dynamic system analysis, our research aims to provide a comprehensive framework for optimizing network supply chain operations. Through a series of case studies and simulations, we demonstrate the effectiveness and potential impact of our proposed methodology in enhancing the resilience and adaptability of network supply chains in the face of uncertainties and disruptions.