.: Hybrid Forecasting

Hybrid forecasting comprises techniques to combine machine forecasting and human judgments. This long has been practiced in the field of meteorology, by running several computer models (machine forecasting) in parallel, often giving significantly different results. Using these models as inputs, meteorologists make judgments on the basis of their expertise. Next, after observing the resulting weather, both the meteorologists and those who design and run the computer models will refine their techniques.

Now the national defense community is seeking to improve forecasts of geopolitical and geoeconomic events through similar techniques. Beginning in 2011, the Intelligence Advanced Research Projects Activity (IARPA) has funded competitions in both machine forecasting of such events, and, separately, human forecasting. Both techniques, using only open source information, have outperformed traditional intelligence community techniques.

Now, IARPA plans research to combine human and machine forecasting via the Hybrid Forecasting Competition. This will include research into best approaches to quantitative modeling for forecasting geopolitical and geoeconomic events (at generally the country-month and country-quarter level) and research to determine optimal protocols for humans to work with machine forecasting systems.

ISIT has been engaging in internal research activities in pursuit of this hybrid forecasting thrust by IARPA.