Grey — Artificial and neural network stochastic volatility model: Intraday return realized volatility forecasting

This paper proposes innovative model for forecasting the trend of intraday scaling behavior of stock market returns from the Taiwan Stock Exchange based on empirically investigating and utilizing database of every-five-minute stock market index. Generally, the movements of stock index prices (returns) are comprehensively influenced by the flow of any new information into the market. For this reason, modeling the volatility of financial time series via stochastic volatility (SV) models has received a great deal of attention in the theoretic finance literature as well as in the empirical literature. Moreover, the directly powerful alternative CRACH-type powerful models are able to explain the well documented varying volatility in time through applying stochastic volatility (SV) model. Consequently, the most contribution of this study is successful to concretely propose the serviceable estimated method and practiced model which results in the higher forecasting accuracy rate than the existing methods and models.