View more articles about
artificial intelligence

Better bidding strategy bodes well for markets

bidding

Analysts are trying to “solve” the problems in the stock market and are seeking an equilibrium for the market—a configuration of bidding strategies under which each participant uses the best strategy possible.

U. MICHIGAN (US)—Computer scientists at the University of Michigan have developed what they say is the best bidding strategy by combining game theory and artificial intelligence.

Michael Wellman, a professor of computer science and engineering, and L. Julian Schvartzman, a doctoral student, say they’ve conducted the most comprehensive continuous double auction strategy study ever published.

Characteristic of the stock market, a continuous double auction is an ever-changing market in which bidders exchange offers to both buy and sell, and transactions occur as soon as participants agree on a price. The process makes it difficult for researchers to study and solve.

Analysts trying to “solve” such problems are seeking an equilibrium for the market—a configuration of bidding strategies under which each participant uses the best strategy possible, while taking into consideration other participants’ strategies.

Schvartzman and Wellman evaluated and tested strategies, including waiting until the last minute to bid, randomly bidding, and taking into account the history of the bids of all participants.

To this evaluation they added a layer of artificial intelligence, or machine learning. This technique enables a computer to, in essence, learn from experimenting with actions in a variety of situations to determine which overall strategy would work best.

“Nobody has put these techniques together before,” Schvartzman says. “One could take these techniques and apply them to real markets, not to predict specific price movements, but to determine the best bidding strategy, given your objectives,” says Wellman.

This new combined method generates a more stable equilibrium candidate comprising stronger bidding strategies than any previously identified, the researchers say. The method, they add, would produce different strategies in different situations.

“My goal is to make a contribution to the automation of markets,” Schvartzman says, “not just financial markets, but in other scenarios, such as Web advertising or even nurses bidding for their shifts in hospitals. Eventually, any resource allocation problem in which there is uncertainty about what something is worth could use a dynamic market instead of a fixed price.”

University of Michigan news: www.umich.edu/news

Related Articles