Lopata Hall, Room 101
Eliciting and Aggregating High-Quality Information from the Crowd
Department of Computer Science
University of British Columbia
Accurate information is essential for solving many problems. Such information often exists as dispersed knowledge and beliefs of many people. I am interested in solving problems by collecting and aggregating a large amount of information contributed by many self-interested individuals. My goal is to motivate participants to provide high-quality information and to aggregate their reports to inform decision making.
In this talk, I will describe two pieces of my work. First, I will introduce prediction markets, which are mechanisms for aggregating information for forecasting future events. Prediction markets outperformed alternative forecasting methods in various settings, but they failed catastrophically at predicting the outcomes of Brexit and the 2016 US presidential election. My work considers scenarios in which prediction markets may fail and offers insights on possible reasons for such failures.
Next, I will tackle the problem of grading assignments in large classes. One way to provide timely feedback to students is peer grading --- having students evaluate one another. A challenge is to motivate students to invest sufficient effort in providing accurate evaluations. I design mechanisms, which provides incentives for effort and accuracy while using limited ground-truth evaluations provided by teaching assistants.
Finally, I will outline my future research agenda on designing effective mechanisms for eliciting and aggregating dispersed information.
Alice Gao is a postdoctoral fellow in Computer Science at the University of British Columbia, advised by Kevin Leyton-Brown. She is generously supported by the Canadian NSERC Postdoctoral Fellowship. Alice's research is on designing mechanisms for eliciting and aggregating dispersed information. Her work has tackled a range of problems including forecasting future events and grading assignments in large classes. Alice obtained her Ph.D. in Computer Science from Harvard University advised by Yiling Chen and her Bachelor's degree in Computer Science and Mathematics from the University of British Columbia.