About TAC

What is a Trading Agent?

Entries in the Trading Agent Competition are software programs designed to trade in electronic markets. We call them "agents" because these programs operate autonomously in the market—sending bids, requesting quotes, accepting offers, and generally negotiating deals according to market rules. Although the agent's activity is ultimately determined by its programmers, the trading behavior is fully automated in that the humans do not intervene while the negotiation is in progress.

Trading agents face a most challenging task. To play the market effectively, an agent must make real-time decisions in an uncertain and fast-changing environment, taking account of other agents doing the same. Capable agents rapidly assimilate market information from many sources, forecast future events, optimize complex offers and resource allocations, anticipate strategic interactions, and learn from experience. Successful trading agents adopt and extend state-of-the-art techniques from artificial intelligence, operations research, statistics, and other relevant fields.

TAC Tournaments

The annual series of trading agent competitions was initiated to promote research and education in the technology underlying trading agents. Research questions include how to design agents and analyze their performance, and how electronic markets behave when populated by autonomous software agents. The TAC series supports such research by providing a common trading scenario and open environment for competing teams to test out their ideas. At the annual competition, the developers of techniques in trading strategy evaluate these ideas, and communicate their results in a public forum for the benefit of the broader research community.

The educational function of TAC is manifest by the significant role of students in the vast majority of teams entering the competition. Many universities use TAC as an exercise for teaching about electronic commerce and artificial intelligence techniques.

Research and education in trading agents promises to improve the state of art and practice in their development, and ultimately lead to more effective electronic markets. Equally important, extending public knowledge in this area promotes understanding of the behavior of autonomous software agents as such systems become more prevalent in commerce, and more broadly in other domains.

Home | Contact Us