A multi-layer Bayesian network method for supply chain disruption modelling in the wake of the COVID-19 pandemic

While the majority of companies anticipated the negative and severe impacts of the COVID-19 pandemic on the supply chains (SC), most of them lacked guidance on how to model disruptions and their performance impacts under pandemic conditions. Lack of such guidance resulted in delayed reactions, incomplete understanding of pandemic impacts, and late deployment of recovery actions. In this study, we offer a method of modelling and quantifying the SC disruption impacts in the wake of a pandemic. We develop a multi-layer Bayesian network (BN) model that can be used to identify SC disruption triggers and risk events amid the COVID-19 pandemic and quantify the consequences of pandemic disruptions. The unique features of BN, such as forward and backward propagation analysis, are utilised to simulate and measure the impact of different triggers on SC financial performance and business continuity. In this way, we combine resilience and viability SC perspectives and explicitly account for the pandemic settings. The outcomes of this research open a novel theoretical lens on application of BNs to SC disruption modelling in the pandemic setting. Our results can be used as a decision-support tool to predict and better understand the pandemic impacts on SC performance.

Automated summary

The study introduces a method of modeling and quantifying supply chain disruption impacts in the pandemic using a multi-layer Bayesian network model, combining resilience and viability perspectives to explicitly account for pandemic settings. The research results can serve as a decision-support tool for predicting and better understanding the pandemic impacts on supply chain performance.