Improving Ensemble Price Prediction in Multi-Agent Market Place to Guide Strategic Sales Decisions

This research focuses on improving ensemble price prediction in multi-agent market places to guide strategic sales decisions. The ensemble price prediction mechanism is implemented in the MinneTAC agent. The MinneTAC agent is an agent-based-computer model developed by the University of Minnesota in cooperation with the Erasmus University. The MinneTAC agent is competing in the Trading Agent Competition for Supply Chain Management (TAC SCM). The TAC SCM competition was developed to come to the best solution of an agent-based-computer model capable of handling a dynamic supply chain. The main goal of this research is to improve the ensemble price prediction mechanism of the MinneTAC agent with techniques like bootstrapping and dynamic economic regime transition probabilities.