Improving realized volatility forecasts using news flow

Improving realized volatility forecasts using news flow

• Author
• Murilo Andre Peres Pereira
• Co-authors
• Marcelo Fernandes
• Abstract

• Economic news may contain valuable information to predict future movements in financial market prices. In this work, we explore the relative importance of news flow to forecast realized volatility. We build text-based indicators using major newspapers in Brazil. Then, we incorporate these indicators into volatility models, controlling for key empirical features, such as asymmetries and discontinuities. Our main results show that the inclusion of news-based variables significantly improve forecasting accuracy. The gains are concentrated in the most liquid stocks and in forecasting horizons above one day.

• Keywords
• realized volatility, NLP, forecasting, newspapers, adaptive lasso.
• Subject Area
• Asset pricing, investments, and Derivatives

Back Download