Disruption evaluation in end-to-end semiconductor supply chains via interpretable machine learning.

COVID-19 has posed unprecedented challenges to global health and the world economy. Two years into the pandemic, the widespread impact of COVID-19 continues to deepen, impacting different industries such as the automotive industry and its supply chain. This study presents a hybrid approach combining simulation modeling and tree-based supervised machine learning techniques to explore the implications of end-market demand disruptions. Specifically, we apply the concept of born-again tree ensembles, which are powerful and, at the same time, easily interpretable classifiers, to the case of the semiconductor industry. First, we show how to use born-again tree ensembles to explore data generated by a supply chain simulation model. To this end, we demonstrate the influence of varying behavioral and structural parameters and show the impact of their variation on specific key performance indicators, e.g., the inventory level. Finally, we leverage a counterfactual analysis to identify detailed managerial insights for semiconductor companies to mitigate adverse impacts on one echelon or the entire supply chain. Our hybrid approach provides a simulation model enhanced by a tree-based supervised machine learning model that companies can use to determine optimal measures for mitigating the adverse effects of end-market demand disruptions. We close the loop of our analysis by integrating the findings of the counterfactual analysis backward into the simulation model to understand the overall dynamics within the multi-echelon supply chain.

Simulating the COVID19-pandemic and its impact on the semiconductor supply chain: Enabling a supply chain risk management framework.

COVID-19 pandemic, in the past 2 years, has affected all aspects of life, as well as businesses with different extents. The fifth wave, pushed by the omicron variant, seems to pave way to a new course of development. In this study we present a hybrid simulation modelling approach using agent-based simulation (AB) and system dynamics (SD). This hybrid model is used to evaluate the pandemic dynamics and its impact on the supply chain (SC) of a semiconductor company. We modelled the infection waves, governmental stringency values, and their impact on demand for several semiconductor applications. Additionally, we simulated vaccination, mutation factors and other recent developments of the pandemic. The results of the epidemiological model show that while the COVID-19 evolved in multiple waves, government restrictions and vaccinations are keys to control the spread of the virus. Moreover, the possible endemic nature of the pandemic fuels the importance of the continuation of our work, as this work will be the backbone of a SC risk management framework: resilient SCs need to be equipped with mitigation measures, to face future challenges. The results of the SC model suggest that mitigation of the COVID-19 disruption could be achieved by having high inventory and/or high global flexibility capacities.