Minimizing the bullwhip effect in a single product multistage supply chain using genetic algorithm

Supply chain management is important for companies and organizations to improve their business and lead competitiveness in the global marketplace. But demand variations in the supply chain are significant problem for most practitioners, planners, demand managers, and operations managers. Demand variations make forecasting and inventory management more difficult and tend to increase inventory levels. The supply chain (SC) profitability can be affected by the cost associated with large inventories, transportation, and production due to the bullwhip effect. Only bullwhip effect can lead to reduce the supply chain profitability in great amount. This paper represents a computational intelligence approach, which addresses the bullwhip effect in multistage supply chain. As a computational intelligence approach, Genetic Algorithm (GA) is employed to reduce the bullwhip effect. Through this approach, optimal order quantity in each stage is to be calculated by considering cost associated with bullwhip effect. Distorted information from one end of a supply chain can lead to tremendous inefficiencies to other end. In this paper it is shown that if each player of the supply chain orders or transfers optimum quantities for the upcoming period then the bullwhip effect can be reduced significantly.