Narratives and future industry and market outcomes

Nicholas Mangee ()

Chapter 11 in Narrative Analytics and Stock Market Forecasting, 2025, pp 147-166 from Edward Elgar Publishing

Abstract: This chapter extends the empirical analysis by considering the narrative intensity explicitly connected to unscheduled corporate events and their corresponding forecasting ability at both the industry and the aggregate market level. The chapter first discusses the industry price and returns data across 12 sectors. This dataset is widely used in the literature and is collected from Ken French's online depository of portfolio sorts. The chapter then introduces the data on unscheduled corporate events, which is initially classified with use of the RavenPack Edge News Analytics platform. The empirical analysis is then presented with a focus on direction of change statistics (DCS) across various forecasting horizons. Direction of change statistics, unlike stochastic measures of coefficient significance, which can be distorted in the presence of structural change, heteroskedasticity, and other statistical contaminants, focus on whether the model forecasts the right-side-of-the-market.

Keywords: Textual news analytics; Ravenpack Edge; Right-side-of-the-market; Industry returns; Unscheduled corporate news events (search for similar items in EconPapers)
Date: 2025
ISBN: 9781035357598
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781035357604.00016 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:24396_11

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Jack Sweeney ().