A generalized concept of a decision-support system for responses to tariff-induced uncertainty and disruptions

In this paper, we present a conceptual design for a decision-support system to address tariff-induced uncertainty and disruptions. The system is comprised of predictive (simulation) and prescriptive (optimization) supply chain analytics supplemented by an LLM module for real-time disruption detection. We illustrate applications of the system developed in AnyLogistix supply chain optimization and simulation software and offer generalized mathematical formulations. The experimental part includes several supply chain stress tests under different tariff scenarios, conducted using discrete-event simulation, and recommendations for proactive supply chain reconfiguration via network optimization. This study has both theoretical contributions and practical implications. For the first time, we conceptualize a decision-support system specifically tailored to the specifics of tariff-induced uncertainty. We also show how the decision-support system proposed can be extended toward a digital twin. Our models can be used immediately in practice for stress testing supply chain resilience and for reconfiguration in response to tariff shocks.