@techreport{119b2ee467e54cf487abe8fb67a8ccde,
title = "Alternative Data for Realised Volatility Forecasting: Limit Order Book and News Stories",
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. ",
keywords = "Realised Volatility Forecasting, Heterogeneous AutoRegressive Models, Limit Order Book Data, News Stories, Sentiment Measures",
author = "Eghbal Rahimikia and Ser-Huang Poon",
year = "2020",
month = sep,
day = "12",
doi = "10.2139/ssrn.3684040",
language = "English",
series = "SSRN Electronic Journal",
publisher = "Social Science Research Network",
address = "United Kingdom",
type = "WorkingPaper",
institution = "Social Science Research Network",
}