WP12
Forecasting Realized Volatility Across Asset Classes: HAR, GARCH, and Machine Learning in a Unified Multi-Asset Horse Race, 2013–2026
The paper compares 27 forecasts of daily realized variance (six HAR specifications, GARCH, GJR, EGARCH and Realized GARCH, penalized regressions, random forests, XGBoost and LightGBM on two information sets, an LSTM, a Transformer, a LightGBM pooled across assets, and two combinations) on 25 liquid instruments from…
Économétrie à haute fréquencerealized volatilityHAR modelGARCHmachine learningWorking draft PDF · 50 pages