Value of information in a serial supply chain under a nonstationary demand process:

Abstract

In this paper, we consider a two level supply chain with a manufacturer supplying the product to a retailer. The retailer faces nonstationary demand that follows an ARIMA (0,1,1) process. In the absence of information sharing, the retailer only conveys his order quantity to the manufacturer, and with information sharing, he also conveys the demand level in each period. The model based on nonstationary demand process is sign cant; given the empirical dings that the demand processes observed in industries such as FMCG, grocery, apparel, and auto components are auto correlated and nonstationary. In our model, we consider a periodic review system for both retailer and manufacturer and derive the expressions for the optimal order up to level for the players. We also obtain the expressions for the cost functions of the two players and conduct a numerical study to evaluate the value of information sharing. We find that both the retailer's ordering process and the manufacturer's demand process are independent of the inertia of the external demand process, and they depend only on the delivery lead time of the retailer from the manufacturer. We observe that both variance of the manufacturer's demand process and his cost decrease due to information sharing. However, the savings in the manufacturer's cost with information sharing decrease as the external demand process becomes less stable or more transitory, and they increase as the demand uncertainty increases. Lastly, we note that the cost reduction is more by reducing the manufacturer's rather than the retailer's lead time.