A two-stage stochastic-robust model for supply chain network design problem under disruptions and endogenous demand uncertainty

A minor disruption can have a disastrous impact as it cascades through a supply chain. In addition, customer demand is uncertain and susceptible to disruption risks and supply chain management decisions, which in turn impacts how well supply chains function during disruptions. In this paper, we address these issues by studying a supply chain network design problem under disruptions and endogenous demand uncertainty. We first propose a two-stage stochastic-robust formulation where disruption risks are represented using a scenario-based approach and the demand is characterized by a box uncertainty set that depends on both facility-location decisions and disruptions. We then develop an adjusted column-and-constraint generation algorithm and conduct extensive evaluations to verify its effectiveness by comparing it with an affine decision rule method. Additionally, We perform out-of-sample tests to assess the effectiveness and robustness of our model compared to two stochastic programming models. Finally, we present managerial insights, examining how the key factors influence supply chain network performance under disruptions, providing practical guidance.