An integrated multi-stage supply chain with time-varying demand over a finite planning horizon is considered in this paper. The objective is to devise the optimal production-inventory policy to minimize the total operational cost. The model is formulated as a mixed integer nonlinear programming problem. The problem is represented as a weighted directed acyclic graph. The global minimum total operational cost is computed in polynomial time by the developed algorithm. Two numerical examples of a seasonal product and a product over its life cycle are studied to illustrate the results. A sensitivity analysis of the system parameters is conducted to assist the supply chain decision makers. (C) 2016 Elsevier B.V. All rights reserved.