Hybrid forecasting of geopolitical events

Author(s)

Daniel M. Benjamin, Nova Southeastern UniversityFollow
Fred Morstatter, USC Information Sciences Institute
Ali E. Abbas, University of Southern California
Andres Abeliuk, University of Chile
Pavel Atanasov, Pytho
Stephen Bennett, University of California Irvine
Andreas Beger, Predictive Heuristics
Saurabh Birari, USC Information Sciences Institute
David V. Budescu, Fordham University
Michele Catasta, Stanford University
Emilio Ferrara, USC Information Sciences Institute
Lucas Haravitch, University of Southern California
Mark Himmelstein, Fordham University
KSM Tozammel Hossain, USC Information Sciences Institute
Yuzhong Huang, USC Information Sciences Institute
Woojeong Jin, USC Information Sciences Institute
Regina Joseph, Sibylink
Jure Leskovec, Stanford University
Akira Matsui, USC Information Sciences Institute
Amandeep Singh, USC Information Sciences Institute
Rok Sosic, Stanford University
Mark Steyvers, University of California, Irvine
Pedro A. Szekely, USC Information Sciences Institute
Michael D. Ward, Predictive Heuristics
Aram Galstyan, USC Information Sciences Institute

ORCID

Daniel M. Benjamin0000-0002-0333-5581

Document Type

Article

Publication Title

AI Magazine

ISSN

0738-4602

Publication Date

3-29-2023

Abstract/Excerpt

Sound decision-making relies on accurate prediction for tangible outcomes ranging from military conflict to disease outbreaks. To improve crowdsourced forecasting accuracy, we developed SAGE, a hybrid forecasting system that combines human and machine generated forecasts. The system provides a platform where users can interact with machine models and thus anchor their judgments on an objective benchmark. The system also aggregates human and machine forecasts weighting both for propinquity and based on assessed skill while adjusting for overconfidence. We present results from the Hybrid Forecasting Competition (HFC)—larger than comparable forecasting tournaments—including 1085 users forecasting 398 real-world forecasting problems over 8 months. Our main result is that the hybrid system generated more accurate forecasts compared to a human-only baseline, which had no machine generated predictions. We found that skilled forecasters who had access to machine-generated forecasts outperformed those who only viewed historical data. We also demonstrated the inclusion of machine-generated forecasts in our aggregation algorithms improved performance, both in terms of accuracy and scalability. This suggests that hybrid forecasting systems, which potentially require fewer human resources, can be a viable approach for maintaining a competitive level of accuracy over a larger number of forecasting questions.

DOI

https://doi.org/10.1002/aaai.12085

Volume

44

Issue

1

First Page

112

Last Page

128

Comments

In memoriam of Michael D. Ward. This paper would not be possible without his contributions.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

NSUWorks Citation

Benjamin, Daniel M.; Morstatter, Fred; Abbas, Ali E.; Abeliuk, Andres; Atanasov, Pavel; Bennett, Stephen; Beger, Andreas; Birari, Saurabh; Budescu, David V.; Catasta, Michele; Ferrara, Emilio; Haravitch, Lucas; Himmelstein, Mark; Tozammel Hossain, KSM; Huang, Yuzhong; Jin, Woojeong; Joseph, Regina; Leskovec, Jure; Matsui, Akira; Singh, Amandeep; Sosic, Rok; Steyvers, Mark; Szekely, Pedro A.; Ward, Michael D.; and Galstyan, Aram, "Hybrid forecasting of geopolitical events" (2023). HCBE Faculty Articles. 1167.
https://nsuworks.nova.edu/hcbe_facarticles/1167