David Pardoe, Peter Stone
The TAC SCM Prediction Challenge presents an opportunity for agents designed for the full TAC SCM game to compete solely on their ability to make predictions. Participants are presented with situations from actual TAC SCM games and are evaluated on their prediction accuracy in four categories: current and future computer prices, and current and future component prices. This paper introduces the Prediction Challenge and presents the results from 2007 along with an analysis of how the predictions of the participants compare to each other.
Subjects: 7.1 Multi-Agent Systems; 12. Machine Learning and Discovery
Submitted: May 5, 2008