A trading agent competition.pdfVIP

The 2001 Trading Agent Competition Michael P. Wellman University of Michigan wellman@ Amy Greenwald Brown University amygreen@ Peter Stone University of Texas pstone@ Peter R. Wurman North Carolina State University wurman@ August 14, 2002 Abstract The 2001 Trading Agent Competition was the second in a series of events aiming to shed light on research issues in automating trading strategies. Based on a challenging market scenario in the domain of travel shopping, the competition presents agents with difficult issues in bidding strategy, market prediction, and resource allocation. Entrants in 2001 demonstrated substantial progress over the prior year, with the overall level of competence exhibited suggesting that trading in online markets is a viable domain for highly autonomous agents. Revised version of a paper to be presented at the Fourteenth Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-02) Contact author. University of Michigan AI Laboratory, 1101 Beal Av, Ann Arbor, MI 48109-2110,USA. Fax: 734-763- 1260. 1 Introduction Automated trading in online markets is increasingly recognized as a promising domain for agent technology. Programmed trading is nothing new, but the emergence of electronic marketplaces has dramatically increased the opportunities for such trading. The trading task may be particularly well- suited for automation, as the interfaces are relatively simple. For example, messages from agents are typically limited to offers to exchange quantities of standardized goods for standardized currency using standardized exchange protocols. Although decisions about desirable trades may be based on a multitude of factors, specifying reasonable strategies seems often quite feasible with normal levels of effort. As researchers we would like to make that last statement more precise, and develop an under- standing of just how effective agent strategies can be, and how automated traders might affect the conduct of electronic markets