Lead-time reduction in a stochastic inventory system with learning consideration

We develop a continuous review inventory model where lead-time is considered as a controllable variable. Lead-time is decomposed into all its components: set-up time, processing time and non-productive time. These components reflect the setup cost reduction, lot size lead-time interaction and lead-time crashing, respectively. The learning effect in the production process is also included in the processing time component of the lead-time. The finite investment approach for lead-time and set-up cost reduction and their joint optimization, in addition to the lot size lead-time interaction, introduce a realistic direction in lead-time management and control. A numerical example and a sensitivity analysis are presented using the design of experiments to investigate the effect of the model parameters and, in particular, those related to the different lead-time components on the the expected total cost.