Latent-Regime Bias Auditing for Volatility Forecasting
2026-08-03 • Machine Learning
Machine Learning
AI summaryⓘ
The authors point out that common ways to check how good volatility forecasts are, like average error measures, might miss problems that only appear in certain market conditions. They developed a method that first identifies different hidden market states using data patterns and then tests if forecasts work well in each of these states separately. When they applied this to cryptocurrency and ETF data, they found that forecasts that looked good on average actually performed poorly in some specific market regimes, especially during extreme events. Their work suggests that evaluating volatility forecasts should consider when and where the predictions fail, not just overall accuracy.
volatility forecastingRMSEMAElatent market regimestime-series representationclusteringtail underpredictioneconomic losscryptocurrencyETF
Authors
Arthur Chagas, Pedro Bento, Yan Aquino, Arthur Buzelin, Wagner Meira, Cristiano Arbex Valle
Abstract
Volatility forecasts are commonly evaluated with aggregate accuracy metrics such as RMSE and MAE, but these metrics can hide conditional failures that matter for risk management. This paper proposes a model-agnostic audit framework for evaluating whether volatility forecasts remain reliable across latent market regimes. We learn time-series representations of market-state windows, cluster them into regimes using only training information, assign regimes out of sample, and compare aggregate forecast behavior with regime-conditional bias, tail-underprediction, and underprediction-sensitive economic losses. Applied to daily volatility forecasting across cryptocurrency and ETF assets, the audit shows that models with competitive aggregate accuracy can still exhibit substantial regime-specific bias and severe tail underprediction. The results suggest that volatility forecasting should be evaluated not only by average error, but also by where and how forecasts become unreliable. Our framework shifts forecast evaluation from asking which model is most accurate on average to identifying the market regimes in which apparently accurate forecasts fail conditionally. Reproducibility: https://github.com/arthurchagas1/Latent-Regime-Bias-Auditing-for-Volatility-Forecasting