Equities
RavenPack | June 12, 2014
In this study, we evaluate the predictive power of RavenPack News Analytics including the Dow Jones and Web Editions across different global markets.
Executive Summary: In this study, we evaluate the predictive power of RavenPack News Analytics including the Dow Jones and Web Editions across different global markets. We find news signals have strongest impact on European markets, followed by Emerging and US markets. We also find that although the Dow Jones Edition generally creates stronger market impact than the Web Edition across all markets, the predictive power from web content improves significantly over recent years. Our study examines the Russell 3000, Russell Europe, and Russell Emerging Markets using a 2-day investment horizon.
Our prior work found the news effect was found to be especially strong for small-mid cap stocks (Russell 2000). There are several possible explanations for the heterogeneous return predictability. First, compared to smaller stocks, large stocks tend to have more venues for information production and dissemination besides public newswires or web releases, which reduces the marginal impact from additional news. Second, market participants tend to follow large stocks more closely and hence absorb new information more efficiently. Last, better liquidity for large stocks provides a stronger cushion from news. In other words, news could play a different role under various information environments and market conditions.
In this paper we use RavenPack’s company sentiment strength indicators (SSI) as an independent return predictor and we find that over short holding horizon (2 or 5 trading days): (1) European markets are most strongly affected by news sentiment, followed by Emerging and US markets; and (2) The Dow Jones Edition generally creates stronger market impact than Web Edition across all markets; (3) the predictive power from the Web Edition improves significantly over recent years.
In the following section, we provide a brief overview of the data used in this paper. In Section 3 we review the company sentiment indicator methodology applied in this study. Section 4 evaluates the return predictability of the indicators generated from Dow Jones, Web, and the combined version in US, Europe, and Emerging Markets. Finally, in Section 5 we present our conclusions.
This research considers the most novel equity news event from both Dow Jones and the more recent Web Edition of RavenPack News Analytics. While the Dow Jones Edition analyzes relevant information from Dow Jones Newswires, regional editions of the Wall Street Journal, and Barron’s, the Web Edition tracks and analyzes more than 22,000 sources including industry and business publishers, national and local news and blog sites, as well as government and regulatory updates. Given the historical data availability for the Web Edition, we restrict our analysis to cover the period January 2007 through December 2013. Our analysis considers three major stocks universes including US, Europe, and Emerging markets.
The European stock universe is based on the Russell Europe index with each stock required to be uniquely mapped to a RavenPack Entity ID. The final sample contains 2,770 European stocks across 22 European countries. UK leads in the European sample with 26.5% of stocks, followed by France with 10.3% and Germany of 8.9%. See Figure 1 for the country distribution of stocks. The European sample stocks are listed on 33 different stock exchanges from three different time zones: CET/CEST, GMT/BST, and EET/EEST. See Appendix B for time zone information for each stock exchange. The news indicator for European stocks is cutoff at 3:30 pm GMT/BST time to allow for order execution.
Please use your business email. If you don't have one, please email us at info@ravenpack.com.
We will process your personal data with the purpose of managing your personal account on RavenPack and offering our services. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability and objection by emailing us at privacy@ravenpack.com. For more information, you can check out our Privacy Policy.
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.