New framework audits volatility forecasts across market regimes

This paper introduces a novel framework for auditing volatility forecasts, moving beyond aggregate accuracy metrics like RMSE and MAE. The proposed method identifies latent market regimes and evaluates forecast reliability within these specific conditions. Applied to cryptocurrency and ETF data, the audit revealed that models with strong average accuracy can still exhibit significant regime-specific biases and tail underpredictions, highlighting the need for more nuanced forecast evaluation. AI

IMPACT Enhances the evaluation of AI models used in financial forecasting by revealing conditional failures.

RANK_REASON The item is an academic paper published on arXiv detailing a new methodology for evaluating forecasting models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• cryptocurrency
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv
• Mae
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →