A new research paper introduces a framework for evaluating forecast reliability using financial risk-adjusted performance measures. The study applies this to U.S. macroeconomic forecasting, comparing econometric benchmarks, machine learning models, and a foundation model against the Survey of Professional Forecasters. Findings indicate that while professional forecasters are hard to outperform on a risk-adjusted basis due to their contextual judgment, certain machine learning methods show promise for specific targets. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Introduces a novel method for evaluating AI forecasting models, potentially improving their adoption in finance and economics.
RANK_REASON Academic paper introducing a new evaluation framework for forecasting models. [lever_c_demoted from research: ic=1 ai=1.0]