Big data and resilience in a milk supply chain: A simulation evaluation

The purpose of this paper is to address the research question: How can data-driven analysis be used to measure time to recovery of the milk supply chain and assess the impact of production and logistics disruptions? This research uses computer simulations of a large milk producers manufacturing facility and SC. Two main types of disruptions were considered: production and logistics disruptions, these were measured against time to recovery. Dynamic capabilities framed the use of big data in sensing disruptions and seizing opportunities to react in a timely manner. The findings show how resilience can be measured in terms of time to recovery. By incorporating the potential of big data for deeper analysis and earlier anticipation of disruptions the detrimental impacts of disruptions were moderated and recovery was faster. The potential impact of using big data to make better predictions of performance earlier in the face of disruptions was demonstrated quantitatively. This is new insight to how resilience can be measured and how disruptions can be moderated.