Hybrid Intelligence Forecasting: A Review

This paper presents a comprehensive review of Hybrid Intelligence Forecasting (HIF), an emerging paradigm that integrates human judgment and machine intelligence to create a better sociotechnical ensemble and enhance forecasting performance.While current iterations of artificial intelligence have achieved substantial success in structured data-rich forecasting tasks, they underperform in complex, uncertain, or data-sparse domains where human judgment remains critical. HIF seeks to combine the complementary strengths of humans and machines through principles of collectivity, superior results, and continuous learning, when used in forecasting. This review evaluates the literature through these three pillars, identifying how forecasts are combined, the impact of trust and forecast correlation, conditions under which hybrid systems outperform individual components, and the challenges of fostering ongoing learning between human and machine agents to devise better sociotechnical ensembles.While hybrid systems often yield improved predictive accuracy in various contexts and across diverse methodologies, significant gaps remain in trust calibration, correlation management, and iterative co-learning. The paper concludes by outlining research directions needed to advance HIF into a robust, adaptive, and trustworthy forecasting paradigm, as well as directions for standardizing HIF studies to better inform the public and private administrations of their value.