Stochastic models for the coordinated production and shipment problem in a supply chain

In this study, we consider the coordination of transportation and production policies between a single supplier and a single retailer in a stochastic environment. The supplier controls the production, holds inventory and ships the products to the retailer to satisfy the external demand. We model the system as a Markov decision process, and show that the optimal production and transportation decisions are complex and non-monotonic. Therefore, we analyze two widely-used shipment policies in the industry as well, namely time-based and quantity-based shipment policies in addition to a hybrid time-and-quantity based shipment policy. We numerically compare the performances of these policies with respect to the optimal policy and analyze the effects of the parameters in the system.

► We analyze the integrated production and dispatch policies in supply chains. ► In the full information model, the optimal solution is non-monotonic and complex. ► Easy to implement time-based, quantity-based and hybrid policies are analyzed. ► Quantity-based policy is superior to the time-based policy in terms of total costs. ► Hybrid policy decreases waiting times substantially with a small increase in cost.