Predicting Zero Bin in the Semiconductor Manufacturing Industry: Machine Learning Algorithms
The semiconductor industry has faced supply chain manufacturing shortages that ultimately led to a worldwide chip shortage during the COVID-19 pandemic. These chip manufacturers use sophisticated and advanced manufacturing machinery in their fabs to manufacture chips. As experienced during the pandemic, manufacturing unavailability is often due to the lack of critical manufacturing-related spare parts. This thesis evaluates the effectiveness of machine learning algorithms to identify significant factors contributing to manufacturing part outages (i.e., zero-bin) to keep manufacturing equipment running at total capacity within the organization. We propose clustering methods to segment the data and use logistic regression, logistic lasso regression, random forest, and kNN approaches to identify important factors for those parts that could go to zero-bin. Extant research applies classic inventory management strategies based on expenditure, criticality, or usage to manage their parts' inventory throughout the year. Instead, the proposed methods explore whether predefined, static inventory parameters can predict whether a spare part reaches zero bin. To demonstrate the viability of this approach, we present a case study using one year's worth of data from a leading chip manufacturing company. Based on the modeling approaches, a lasso-based logistic regression proved the best predictive model amongst the five clusters with lead-time, current quantity available, days on inventory (usage remained relevant), and the part's reorder point being the most significant parameters.
Montoya, Yazmin, "Predicting Zero Bin in the Semiconductor Manufacturing Industry: Machine Learning Algorithms" (2021). ETD Collection for University of Texas, El Paso. AAI28869349.