Volatility Forecasting: The Role of Internet Search Activity and Implied Volatility
49 Pages Posted: 21 Jul 2016 Last revised: 4 Aug 2018
Date Written: July 30, 2018
Recent empirical literature shows that Internet search activity is closely associated with volatility in financial and commodity markets. We evaluate the role of the Internet search activity in forecasting realized volatility using benchmark models that include market-based variables. We conduct not only in-sample but also recursive, window-size robust out-of-sample analysis. In both in-sample and out-of-sample models, the predictive power of the Internet search activity data disappears in the financial markets and substantially diminishes in the commodity markets once implied volatility is included. A common component analysis shows that most of the predictive information contained in the Internet search activity is also present in implied volatility while implied volatility has additional predictive information that is not contained in the Internet search activity.
Keywords: Volatility forecasting, realized volatility, implied volatility, Internet search activity, Google Trends search volume index, information
JEL Classification: C32, C52, G12, G14, G17
Suggested Citation: Suggested Citation