Managing the Supply Chain with Intelligent Software Agents Using an Asymmetric Cost Function

Using an exact replication of the MIT Beer Game, a supply chain simulation was developed in which Intelligent Software Agents manage the supply chain subject to all of the constraints placed on the original human players. The agents’ information processing capabilities are founded on Support Vector Machines (SVM) with an asymmetric cost function, which permits internal modeling of appropriate safety stock levels. Additionally, these agents learn patterns from new information as the game simulation progresses. The simulation results indicate that intelligent agent-managed supply chains outperform those managed by humans.