Supply chain management is a critical aspect of modern business operations, especially in the context of globalization. As supply chains become increasingly complex and interconnected, companies face new challenges in ensuring resilience and minimizing risks. This paper presents an approach to supply chain risk management that integrates machine learning and graph-based analytics to identify and mitigate critical vulnerabilities, or "hotspots," within the supply network. By leveraging Graph Neural Networks (GNNs) and optimization models, we propose a scalable and automated system capable of detecting risks and generating proactive mitigation strategies. The study further evaluates the performance of the system against traditional risk management techniques.     «

Supply chain management is a critical aspect of modern business operations, especially in the context of globalization. As supply chains become increasingly complex and interconnected, companies face new challenges in ensuring resilience and minimizing risks. This paper presents an approach to supply chain risk management that integrates machine learning and graph-based analytics to identify and mitigate critical vulnerabilities, or "hotspots," within the supply network. By leveraging Graph Neur...     »