![[speaker photo]](http://ee380.stanford.edu/Abstracts/160309-speakerphoto.png)
We report the results of a four year experiment in which over twenty thousand volunteers made predictions about hundreds of real world geopolitical events in dozens of carefully controlled experiments, all designed to answer questions about what interventions increase the accuracy of forecasts. What traits do good forecasters share? How important is domain expertise? Can training improve forecasts? How should forecasts be elicited--surveys or prediction markets? How should that wisdom be combined? What clever statistical aggregations work best?
Joint work with Phil Tetlock, Barbara Mellers, and the Team Good Judgment, all at the University of Pennsylvania.
Slides:
No slides from this talk are available for download at this time.
Videos:
About the speaker:
|
|
Dr. Lyle Ungar is a Professor of Computer and Information Science at the University of Pennsylvania, where he also holds appointments in multiple departments in the Schools of Business, Medicine, Arts and Sciences, and Engineering and Applied Science. Lyle received a B.S. from Stanford University and a Ph.D. from M.I.T. He has published over 200 articles and in co-inventor on eleven patents. His current research focuses on developing scalable machine learning methods for data mining and text mining, including spectral methods for natural language processing, statistical models for aggregating crowd-sourced predictions, and techniques to analyze social media to better understand the drivers of physical and mental well-being. |
Contact information:
Lyle Ungar
ungar@cis.upenn.edu