NEURAL-NETWORK IDENTIFICATION OF CRITICAL FACTORS IN A DYNAMIC JUST-IN-TIME KANBAN ENVIRONMENT

Prior research has examined the proper number of kanbans to be used in various just-in-time environments, but relatively little work has bee n done in exploring which factors internal and external to a shop in a given time period are critical in determining the necessary number of kanbans to be specified for the next period. The research reported he re examines the identification of shop factors in a dynamic and stocha stic just-in-time environment. In particular, three questions are addr essed: does information from a prior period help in setting the kanban level in the current period? If so, which endogenous and exogenous fa ctors considered individually help the most? And finally, what groupin g of individual factors is most important in deciding the number of ka nbans? The methodology employed is to use artificial neural networks t o fit simulated shop data to learn the relationship between prediction factors and overall shop performance. Appropriate non-parametric stat istical tests are then used to answer the questions. The answers obtai ned, although shop specific, may also be generated by firms willing to follow the procedure presented here for conditions specific to their particular operation.