Designing Markets for Prediction
Yiling Chen (Harvard University)
CSE 520 Colloquium
Thursday, November 29, 2012, 3:30pm
EEB-105
Abstract
Suppose that you are interested in estimating the probability that the US unemployment rate in February 2013 will be greater than 10%. You might choose to ask an expert, dig through news articles, or run a regression with historical data to come up with a reasonably well-informed guess. But you might be able to obtain an equally good and often better estimate by appealing to the wisdom of crowds and asking the market.
A prediction market is a betting intermediary designed to aggregate information. It offers contracts whose payoff is tied to outcomes of an event of interest and attracts participants to trade the contracts.
For instance, a contract that pays $1 if the US unemployment rate in February 2013 is greater than 10% and $0 otherwise can be used to predict the likelihood that the employment rate will soar. If the current market price of the contract is $0.3, a rational, risk-neutral trader should be willing to buy the contract if he believes the true probability for the unemployment rate to be greater than 10% is greater than 0.3. Conversely, he should be willing to sell the contract if he believes the true probability is lower than 0.3. The market price hence incorporates the information of participants and approximately represents a real-time consensus forecast for the event.
In this talk, I will discuss how to better design market mechanisms for the purpose of information aggregation and present some results on designing combinatorial prediction markets that offer more expressiveness for traders to reveal their information, among other desirable properties.
Bio:
Yiling Chen is an associate professor of computer science at Harvard School of Engineering and Applied Sciences. She is a member of the EconCS and AI research groups, and a faculty affiliate of the Center for Research on Computation and Society (CRCS).
Prior to Harvard, she spent about two years at the Microeconomics and Social Systems group of Yahoo! Research in New York City. She obtained her Ph.D. from the College of Information Sciences and Technology at The Pennsylvania State University. She is a recipient of an NSF CAREER Award and was recognized by IEEE Intelligent Systems as one of AI's 10 to Watch in 2011.