GAMBITY
LIVE

Good Judgment Open

Harnessing the wisdom of crowds and Superforecasters to predict world events.

Founded
2015
Valuation
—
Regulated
❌ No
Gambity Prestige
Active
Good Judgment Superforecasters outperforming AI ensembles on complex geopolitics through 2028
88%
— Victoria Blackwell

Good Judgment Open (GJ Open) was launched in 2015 as the public-facing forecasting portal of Good Judgment Inc, a commercial spin-off originating from the landmark Good Judgment Project (GJP). Co-founded by Wharton professors Philip Tetlock and Barbara Mellers alongside UC Berkeley professor Don Moore, the platform stems from research funded by the US Intelligence Advanced Research Projects Activity (IARPA) Aggregative Contingent Estimation (ACE) tournament, which demonstrated that well-calibrated crowd ensembles systematically outperformed professional intelligence analysts.

Unlike financial orderbook prediction exchanges that rely on real-money or cryptocurrency pricing, GJ Open operates as a non-monetary, probability-based forecasting engine. Participants submit percentage probabilities on complex geopolitical, macroeconomic, public health, and environmental questions. Individual predictions are tracked over time and evaluated using Brier accuracy scores—a mathematical metric measuring probabilistic calibration and resolution accuracy.

GJ Open serves as both a public intellectual utility and a global talent identification framework. Top-performing forecasters who consistently land in the top 1–2% of probabilistic accuracy are invited to join Good Judgment Inc's elite commercial "Superforecaster" panels. These Superforecaster ensembles deliver calibrated risk assessments and strategic intelligence feeds to corporate strategy desks, sovereign wealth funds, and international policy institutions.

Timeline
2011
Good Judgment Project Launched
Philip Tetlock, Barbara Mellers, and Don Moore establish GJP under IARPA's ACE forecasting initiative.
2015
Good Judgment Open Launch
Good Judgment Inc launches GJ Open as a public forecasting portal and talent identification platform.
2015
Superforecasting Publication
Tetlock co-authors "Superforecasting: The Art and Science of Prediction," detailing GJP's methodology and insights.
2020
Global Pandemic Risk Tracking
Deploys rapid-response forecasting challenges tracking COVID-19 epidemiology, vaccine timelines, and economic recovery.
2026
AI vs. Human Ensemble Benchmarking
Integrates probability data feeds comparing Superforecaster ensembles against LLM-based predictive agents for enterprise clients.
Frequently Asked
Good Judgment Open was created by decision science researchers Philip Tetlock, Barbara Mellers, and Don Moore following the success of the IARPA-funded Good Judgment Project.
No, GJ Open is a non-monetary platform where users submit percentage probability forecasts that are scored using Brier accuracy metrics.
A Superforecaster is an individual whose long-term track record places them in the top 1% to 2% of probabilistic accuracy across diverse domain topics.
Forecasts are scored using the Brier score, a mathematical formula that rewards both calibration (expressing confidence proportional to probability) and resolution (assigning high probability to events that happen and low to those that do not).
Questions span global geopolitics, elections, macroeconomic policy, public health, climate change, and technology milestones.
Also in Pitch
Metaculus
Metaculus
The platform where physicists decided that forecasting the end of the world was too important to leave to markets.
Manifold Markets
Manifold Markets
Create a prediction market on anything in seconds.
Futuur
Futuur
Crowdsourced forecasting across politics, science, climate, and pop culture.
← Back to Pitch