Competitive business simulation: Lessons learned from the Trading Agent Competition

In the fast-evolving online business environment, there is a growing need for technologies that empower participants to rapidly evaluate very large numbers of alternatives in the face of constantly changing market conditions. AI and machine-learning techniques are routinely used in support of automated trading scenarios, but the deployment of these technologies remains limited, and their proprietary nature precludes the type of open benchmarking that is critical to scientific progress.  Many important developments in artificial intelligence have been stimulated by organized competitions that tackle interesting, difficult challenge problems, such as chess, robot soccer, poker, robot navigation, stock trading, and others. Economics and artificial intelligence share a strong focus on rational behavior. Yet the combination of limited
observability, high variability, and real-time demands of many domains do not lend themselves to traditional assumptions of rationality. This is the case in many trading environments, where self-interested entities must decide and act subject to limited time and information.

This talk will focus on the problem of designing and constructing competitive simulation environments for autonomous decision-making agents (and possibly human users) that combine research relevance with tractability and value to business and society. Much of the focus will be on two very different Trading Agent Competition scenarios, the Supply Chain Management and Power competitions.