Comparison of two clustering approaches to find demand patterns in semiconductor supply chain planning

Advancements in semiconductor industry have resulted in the need for extracting vital information from vast amount of data. In the operational process of supply chain, understanding customer demand data provides important insights for demand planning. Clustering analysis offers potential to identify latent information from multitudinous customer demand data and supports enhanced decision-making. In this paper, two clustering algorithms to identify customer demand patterns are presented, namely K-means and DBSCAN. The implementation of both algorithms on the prepared data sets is discussed and their performance is compared. The paper outlines the importance of deciphering valuable insights from customer demand data in the betterment of a distributed cognitive process of demand planning.