Supply Chain Design For Supply Chain Resilience: A Case Study Of A Coffee Company

Abstract

This study focuses on applying digital twins to supply chain of ABC coffee company that combines optimization techniques, machine learning, and simulation to improve decision-making processes. The optimization focuses on aligning the supply chain's inputs, like customer expectations, product details, suppliers, production, and distribution center specifics, with the aim to enhance efficiency and reduce costs. Greenfield Analysis and Network Optimization are central components of Optimization, indicating a methodical approach to designing and improving the supply chain network. Machine learning is applied to predict potential disruptions by area, with a specific mention of events like those experienced during COVID-19. This predictive capability is essential for proactive supply chain resilience. The simulation component tests the system's responses to various scenarios, assessing the outcomes of disruptions and optimization strategies. The result of the simulation dictates whether the current model is sufficient or if further recommendations are necessary to improve the system. In essence, the model from this study outlines a robust supply chain management strategy that is data-driven, adaptable to change, and resilient to disruptions.