FEDS Paper: Linear and Nonlinear Econometric Models versus Machine-Learning Models: Evidence from Realized-Volatility Forecasting(Revised)

Rehim KilicThis paper examines which representations of persistence and nonlinearity are most useful for forecasting realized volatility and whether machine learning adds value beyond econometric models designed for long memory and regime dependence. We compare HAR, ARFIMA, threshold HAR, smooth-transition HAR, and Markov-switching HAR with XGBoost and several neural-network models for the S&P 500 and 40 U.S. equities.

FT Wealth: September

In this edition: The elusive tycoon who bought into Cuba’s cigar trade; how philanthrophy is responding to the rise of AI; the brand extension that’s a wrong turn for Ferrari; wealthy investors are filling the world’s vaults with physical gold; Britain’s churches need a miracle to keep the roof on

Pages

Subscribe to Front page feed