University of Pennsylvania Perry World House, A Roadmap to Implementing Probabilistic Forecasting Methods
Crowdsourced forecasting is a process that enables a large group of people to combine their individual forecasts into a “crowd” or “consensus” forecast that often generates a more accurate forecast than individual experts.
INFER gets requests from policymakers about what they need to understand about the future. We then agree on a question that best represents what they want to know. From there, our team goes through a process of “decomposing” that broad question into the individual questions you see on INFER.
Learn more about our decomposition process.
INFER creates regular reports of forecasting outputs for policymakers to use in their analysis and decision-making process. These come in the form of quarterly updates, or alerts about notable movement in the consensus forecasts.
INFER is run by the Applied Research Laboratory for Intelligence and Security (ARLIS) at the University of Maryland, a University Applied Research Center (UARC) funded by the Department of Defense, in partnership with Cultivate Labs.
INFER supports U.S. Government policymakers in elements of the Department of Defense, Intelligence Community, State Department, and other Departments throughout government.
By leveraging the power of the crowd, the goal of INFER is to provide early warning and a more diverse perspective about the future to bolster the national security and intelligence of the U.S. and its allies.
If you are a policymaker interested in working with INFER on a strategic question or issue, or have a community of people who would be interested in making forecasts, contact us at
— Anthony Cordetti, INFER forecaster
— Trisha Ray, INFER forecaster