Keyword Tag Sort by


Categories: Game theory Engineering Computer Science Bidding strategies Artificial Intelligence

Game theory and machine learning offer better bidding strategies

ANN ARBOR, Mich.—By combining techniques from game theory and artificial intelligence, computer scientists at the University of Michigan have developed a better way to find the best bidding strategy in a simulated auction modeled after commodity and financial securities markets.

Michael Wellman, a professor in the Division of Computer Science and Engineering; and L. Julian Schvartzman, a doctoral student, will present their findings May 15 at the International Joint Conference on Autonomous Agents and Multiagent Systems in Budapest, Hungary.

The researchers say they've conducted the most comprehensive continuous double auction strategy study ever published. 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. This dynamic behavior is characteristic of the stock market, for example. And it makes such markets difficult for researchers to study and solve.

Analysts trying to "solve" such problems are seeking an equilibrium for the market. An equilibrium is a configuration of bidding strategies under which each participant uses the best strategy he or she can, taking into consideration the other participants' strategies.

Schvartzman and Wellman evaluated and tested all prior proposals for the best strategies, which include 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. The "reinforcement learning" technique they used enables a computer to, in essence, learn from experimenting with actions in a variety of situations to determine what overall strategy would work best.

"Nobody has put these techniques together before," Schvartzman said.

"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," Wellman said.

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

"My goal is to make a contribution to the automation of markets," Schvartzman said, "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."

The paper is called, "Stronger CDA strategies through empirical game-theoretic analysis and reinforcement learning." This research is funded by the National Science Foundation.

Michigan Engineering:
The University of Michigan College of Engineering is ranked among the top engineering schools in the country. At more than $130 million annually, its engineering research budget is one of largest of any public university. Michigan Engineering is home to 11 academic departments and a National Science Foundation Engineering Research Center. The college plays a leading role in the Michigan Memorial Phoenix Energy Institute and hosts the world class Lurie Nanofabrication Facility. Find out more at http://www.engin.umich.edu/.

Related Link: Michael Wellman

Contact: Nicole Casal Moore, Phone: (734) 647-1838

Source: University of Michigan

Related News:

Graphene membranes may lead to enhanced natural gas production,... 8 October 2012, 13:34
Engineering faculty and students at the University of Colorado Boulder have produced the first...

Mimicking the Brain, in Silicon 15 November 2011, 04:11
New computer chip models how neurons communicate with each other at synapses. CAMBRIDGE, Mass....

Researchers Turn Viruses Into Molecular Legos 20 October 2011, 11:23
BERKELEY — Researchers at the University of California, Berkeley, have turned a benign virus...

Golden touch makes low-temperature graphene production a reality 12 October 2011, 10:18
A method which more than halves the temperature at which high-quality graphene can be produced...

Phone losing charge? Technology created by UCLA engineers allows... 10 August 2011, 05:03
With photovoltaic polarizers, devices could be powered by sunlight, own backlight.We've all...

Graphene optical modulators could lead to ultrafast communications 9 May 2011, 06:08
BERKELEY — Scientists at the University of California, Berkeley, have demonstrated a new...

Software Creates Privacy Mode To Help Secure Android Smartphones 13 April 2011, 09:52
Researchers at North Carolina State University have developed software that helps Android...

Novel Nanowires Boost Fuel Cell Efficiency 31 March 2011, 11:09
New Haven, Conn. — Fuel cells have been touted as a cleaner solution to tomorrow's energy...

New fluorescent OLEDs display greater efficiencies than believed... 23 March 2011, 14:10
ANN ARBOR, Mich.—University of Michigan engineering researchers have designed an exceptionally...

Southampton scientists develop control system to allow spacecraft... 14 February 2011, 17:58
The world’s first control system that will allow engineers to programme autonomous satellites...