We propose an automatic machine-learning system to forecast realized volatility for S&P 100 stocks using 118 features … extraordinary performance across forecast horizons, and the improvement in out-of-sample R2's translates into nontrivial economic …

We augment the HAR model with additional information channels to forecast realized volatility of WTI futures prices …

particular ensemble models and neural network models. Most interestingly, we are the first to consider the “forecast combination …