Press Release

Johns Hopkins APL Wins IARPA Geopolitical Forecasting Challenge

The Johns Hopkins Applied Physics Laboratory (APL) in Laurel, Maryland, earned first place overall and Election Forecaster honors in the Intelligence Advanced Research Projects Activity (IARPA) Geopolitical Forecasting Challenge.

IARPA created the challenge as a way for the intelligence community to develop innovative ways to use crowdsourced forecasts and other data to predict potentially disruptive geopolitical events.

For seven months, competing teams were tasked to submit predictions for 165 questions on various geopolitical topics, such as whether any NATO member would invoke Article 4 or Article 5 of the North Atlantic Treaty, whether Afghanistan’s president would experience a significant leadership disruption, or how many Middle Eastern countries might return their ambassador to Qatar. For each open question — sometimes there were 80 questions open at the same time — a forecast needed to be submitted every day.

All teams were given access to forecasts produced by hundreds of human experts. The APL team, named DigitalDelphi and including Anna Buczak, Dan Berman, Jared Zook and Kayla Scharfstein (with help from James Howard and Welton Chang), topped 16 other teams by scoring the most points in the overall challenge and in the Elections sub-challenge. The Elections sub-challenge included questions related to who will win elections in a number of countries, including Hungary, Iraq, Mexico and Colombia.

“Someone once said, ‘It is difficult to make predictions, especially about the future,’” said Buczak, chief scientist in APL’s Air and Missile Defense Sector and the team lead. “That accurately describes the difficulty of making true predictions in the Geopolitical Forecasting Challenge. But we have a solid, talented team that does its homework and knows how to find trends and indicators in wide collections of data.”

For more on the IARPA Geopolitical Forecasting Challenge, visit https://www.iarpa.gov/challenges/gfchallenge.html.