Robust Forecast Aggregation

2017/10/08 by Itai Areili, Yakov Babichenko, Areili, Itai +3 · 3 citations
Decision Sciences · Economics, Econometrics and Finance · Physics and Astronomy · #Complex Systems and Time Series Analysis #FOS: Economics and business #Forecasting Techniques and Applications #General Economics (econ.GN) #Opinion Dynamics and Social Influence

paper · pdf · doi:10.48550/arxiv.1710.02838

openalex publication_date 2017/10/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Bayesian experts who are exposed to different evidence often make contradictory probabilistic forecasts. An aggregator, ignorant of the underlying model, uses this to calculate her own forecast. We use the notions of scoring rules and regret to propose a natural way to evaluate an aggregation scheme. We focus on a binary state space and construct low regret aggregation schemes whenever there are only two experts which are either Blackwell-ordered or receive conditionally i.i.d. signals. In contrast, if there are many experts with conditionally i.i.d. signals, then no scheme performs (asymptotically) better than a (0.5,0.5) forecast.

Citations

• A solution to the single-question crowd wisdom problem

Cited by

• Multi-agent Adaptive Mechanism Design
• Robust forecast aggregation via additional queries
• Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information

Related

• The Surprising Benefits of Base Rate Neglect in Robust Aggregation
• Peer Expectation in Robust Forecast Aggregation: The Possibility/Impossibility
• Learning of Optimal Forecast Aggregation in Partial Evidence Environments
• Algorithmic Robust Forecast Aggregation
• A Generative Bayesian Model for Aggregating Experts' Probabilities