An Overview of the Role of Data-driven Modeling and Big Data Analytics in Building a Resilient Supply Chain Digital Twin

Data-driven analysis and model-based methods represent a vision of future decision support systems (DSS) in risk management of supply chain disruptions. Data-driven disruption modeling provides a basis for the proactive and resilient design of the supply chain in predicting disruptions and parametric-structural adaptation in the event of a disruption. This modeling is a combination of simulation, optimization, and data analytics to create a digital supply chain twin and thereby manage the risks of disruptions. In this article, we examine the role of data-driven modeling based on the simultaneous use of simulation and optimization, i.e., the supply chain digital twin, as well as the role of big data analytics in resilient supply chains. We will have an overview of some previous researches in the literature to examine the effect of big data analytics in creating disruption scenarios, preventing disruptions, and building recovery policies in the event of a disruption, which leads to supply chain risk management and creating a resilient supply chain. We will also review the role of the supply chain digital twin in supply chain risk analysis and creating a resilient supply chain that enables the simulation of the dynamic behavior of the supply chain and supports model-based decision-making. Finally, the features of anyLogistix software, which provides the possibility of modeling the supply chain digital twin, will be examined.

Keywords:

Supply Chain Resilience , Supply Chain Digital Twin , Big Data analytics , data-driven analysis , Supply chain risk management