What is it about?
What is the most effective way for tapping into crowd wisdom? We describe the first large-scale, experimental comparison between crowd prediction methods. We compare prediction markets, a popular method for eliciting forecasts through bets, with prediction polls, in which forecasts provide probability estimates about future events and receive feedback about their accuracy. Prediction polls should not be confused with opinion polls, which elicit subjective attitudes and voting intentions, not verifiable forecasts.
Featured Image
Why is it important?
Public and private sector organizations spend billions on making predictions, on topics like geopolitical risks, economic developments and product success. We experimentally compare two crowd forecasting methods, markets and polls, and discuss the arguments for deploying each method in organizational settings. Managers, whose work depends on forming realistic expectations and anticipating future risks, will benefit from using these methods to tap into crowd wisdom.
Perspectives
I believe the work described here will provide an important perspective for thinking about prediction markets, as chatter about the 2016 Presidential Election heats up. Prediction markets are billed as the best method for collecting crowd wisdom about elections. This work provides new insights as to when and why prediction markets work. My hope is that our research, together with other research in the Good Judgment Project, will contribute to the trend of growing adoption of prediction methods in public tournaments and inside organizations.
Dr Pavel Atanasov
University of Pennsylvania
Read the Original
This page is a summary of: Distilling the Wisdom of Crowds: Prediction Markets vs. Prediction Polls, Management Science, March 2017, INFORMS,
DOI: 10.1287/mnsc.2015.2374.
You can read the full text:
Contributors
The following have contributed to this page
