A0224
Title: Forecasting realized volatility: Does anything beat linear models?
Authors: Alexandre Rubesam - IESEG School of Management (France) [presenting]
Mauricio Zevallos - University of Campinas (Brazil)
Rafael Branco - University of Campinas (Brazil)
Abstract: The performance of several linear and nonlinear machine learning (ML) models is evaluated in forecasting the realized volatility (RV) of ten global stock market indices in the period from January 2000 to December 2021. Models are trained using a dataset that includes past values of the RV and additional predictors (composed of lagged returns and macroeconomic variables) and compared to widely used heterogeneous autoregressive (HAR) models. The main conclusions are that (i) the additional predictors improve the out-of-sample forecasts of 1-day-ahead RV; (ii) no evidence s found that nonlinear ML models can statistically outperform linear models; and (iii) all ML models show a tendency to underestimate the RV in high-volatility periods, and overestimate the RV in low-volatility periods.
