A comparison of artificial neural networks and decision trees for the kanban setting problem

Determining the number of circulating kanban cards is important to the effective operation of a just-in-time with kanban production system. While a number of techniques exist for setting the number of kanbans, artificial neural networks (ANN) and classification and regression trees (CART) represent two practical approaches with special capabilities for operationalizing the kanban setting problem. This paper provides a comparison of ANNs with CART for setting the number of kanbans in a dynamically varying production environment. Our results show that both methods are comparable in terms of classification accuracy, but that CART has advantages in terms of explainability and shorter development times.