Realized volatility forecasting based on rolling SW-SVR method: evidence from CSI 300 index

In this article, we examine realized volatility forecasting based on a new data-driven method, named rolling SW-SVR method. The empirical evidences from the high frequency data of CSI 300 index show that this new method has stronger out-of-sample forecasting ability than the OLS and SVR methods. Its forecasts ability is stable among different forecast horizons, which is confirmed by the out-of-sample $${{\bf{\it{R}}}^2}$$R2 and the MCS test.