Modelling Framework to Aid A Decision-Maker Assess Supply Chain Resilience to Source Stress Under Uncertainty and Limited Visibility

There is increasing interest in the resilience of supply chains given the growing awareness of their vulnerabilities to natural and man-made events. Covid-19 is one recent example where supply chain vulnerabilities have been exposed. In the academic literature, there has been limited consideration of how the impact of stress on the sources of supply can be modelled to understand resilience of the supply chain from the perspective of decision-makers in the focal firm. In particular, taking into account the actual visibility the focal firm can have to the extended supply chain network members. This paper addresses this challenge by proposing a novel modelling framework using Dynamic Bayesian networks to analyse the supply chain resilience and the feasibility of managerial choices by the focal firm to mitigate the effects of the stress in the supply sources. The framework aims to make appropriate use of available data, both relevant historical empirical data combined with structured subjective data from the decision-maker, so that the model represents the impact of supply source stress through the evolution of the effects of uncertainty over time. We show how the output of Dynamic Bayesian network model can be translated to provide the monetary impact of different managerial choices to the aid decision-maker assess whether early intervention can limit the impact of stress in the supply sources. The modelling principles of our framework are illustrated for an example based on a real, de-sensitised, industry case study.