Alternative Data for Realised Volatility Forecasting: Limit Order Book and News Stories

Research output: Preprint/Working paperWorking paper

Abstract

This study evaluates the predictive power of the limit order book (LOB) and news stories for forecasting realised volatility. We find that during periods of high volatility, the news count variable provides more predictive power compared to various news sentiments. Furthermore, LOB depth proves to be more informative than LOB slope. During the COVID-19 pandemic, the impact of news count was more pronounced than that of LOB depth. Interestingly, on days with normal volatility, the market appears to be predominantly influenced by buying pressure, which shifts in the opposite direction on high volatility days. Additionally, our findings reveal a consistent trade-off in forecasting performance between normal and high volatility days. Various forecasting evaluation tests and alternative model specifications confirm the robustness of our results.
Original languageEnglish
PublisherSocial Science Research Network
Number of pages44
DOIs
Publication statusPublished - 12 Sept 2020

Publication series

NameSSRN Electronic Journal
PublisherSocial Science Research Network
ISSN (Print)1556-5068

Keywords

  • Realised Volatility Forecasting
  • Heterogeneous AutoRegressive Models
  • Limit Order Book Data
  • News Stories
  • Sentiment Measures

Research Beacons, Institutes and Platforms

  • Institute for Data Science and AI

Fingerprint

Dive into the research topics of 'Alternative Data for Realised Volatility Forecasting: Limit Order Book and News Stories'. Together they form a unique fingerprint.

Cite this