The impact of exponential smoothing forecasts on the bullwhip effect

Abstract

An important phenomenon often observed in supply chain management, known as the bullwhip effect, implies that demand variability increases as one moves up the supply chain, i.e., as one moves away from customer demand. In this paper we quantify this effect for simple, two-stage, supply chains consisting of a single retailer and a single manufacturer. We demonstrate that the use of an exponential smoothing forecast by the retailer can cause the bullwhip effect and contrast these results with the increase in variability due to the use of a moving average forecast. We consider two types of demand processes, a correlated demand process and a demand process with a linear trend. We then discuss several important managerial insights that can be drawn from this research.

Stability of information‐sharing alliances in a three‐level supply chain

“…In addition, if the retailer is the strongest among the three supply chain members (e.g., Wal-Mart), he may influence the formation of the outcome that he likes best (say, the grand coalition 6 ), while a strong manufacturer may encourage the formation of an information-sharing agreement that includes only the retailer and the distributor. 7 Recall that we assumed equal bargaining power among all supply chain members and did not take this type of relationships into account; relaxing this assumption would imply that players' preferences for different coalition structures may change as well, which could ultimately lead to different stable outcomes. We feel that this may be an interesting area of future research.…”

“…Thus, the underlying demand process can be represented with a one-period autoregressive model, AR (1). Chen et al [7] extend the analysis to multiple-level supply chains and show that the bullwhip effect can be reduced (but not completely eliminated) in the presence of information sharing. A similar model of customer demand is used by Lee et al [20], who analyze the impact of the autocorrelation coefficient and the lead time on the benefits from information sharing in a two-stage supply chain.…”

Dynamic simulation and optimal control strategy of a decentralized supply chain system

“…It is clear that the customer demand variations can be viewed as a stochastic process. A mature control scheme that could be used for stochastic process control is the minimum variance control scheme [9][10][11][12] . The objective of this work is to show that, by using MVC to control inventory at hand and inventory on the road, changes in demand can be successfully tracked, excess inventory and backorder are minimized, and the ordering bullwhip can be effectively suppressed as well.…”

Supply chain performance evaluation: a simulation study

“…al., 2000; Chen, et. al., 2000), the following auto-regression process is used to describe the end demand whered(k) = is the end demand for the two product types at day k. In (I), dio is a positive constant, and o, is an i.i.d.…”

“…The parameters diu and dzo describing the end demand process in (1) are chosen as dio = d20 = 12. The lead time of D is small as compared to manufacturers' lead times With LD = 1 day.…”