Equities
RavenPack | January 15, 2014
In this paper we explore the characteristics of RavenPack’s new data set derived from online public sources of financial news and opinion compared to content published by Dow Jones & the Wall Street Journal.
Executive Summary:
In this study, we explore the characteristics of RavenPack’s new data set derived from online sources of financial news and opinion compared to the real-time content published by Dow Jones & the Wall Street Journal. Overall, we find the web is catching up in terms of reporting novel corporate events. Adding web sources improves both company and event coverage . By intersecting company sentiment from RavenPack’s Dow Jones Edition and the new Web Edition, we show how to improve a simple reversal strategy. Our study examines all Russell 3000 constituents using a 1-week investment horizon.
Combining premium newswire services with broader web content significantly improves return predictability:
RavenPack has recently enhanced its flagship RavenPack News Analytics (RPNA) product with over 22,000 online sources of financial news and opinion. RavenPack News Analytics Version 3.X now includes 7 years of historical data from web publications and blogs – adding to the 14-year archive of Dow Jones newswire content. The event count for the Web Edition, as the data from web content is known, has increased significantly in recent years and generates over 2 times more events than Dow Jones in 2013. Generally, the Web Edition has more news events across most groups. The web content not only increases the overall event count, but also potentially improves timeliness and provides new informational content.
Before tapping into the additional news sources, at least two questions are of paramount interest: (1) whether the different new sources contain value on their own; and (2) whether the new Web sources complement the existing Dow Jones newswire content. To answer these questions, this study conducts a horse race comparison between a set of company sentiment indicators generated from the Dow Jones Edition and the Web Edition.
Using one of RavenPack’s company sentiment indicators as a signal overlay on a simple short-term reversal model, we find that (1) the Dow Jones and Web Editions each contain valuable information in terms of future return predictability; and (2) the Web Edition has complementary value beyond the Dow Jones dataset.
In the following section, we provide a brief overview of the data used in this paper. In Section 3, we present the key statistics for the Dow Jones and Web Editions of RavenPack News Analytics 3.X. In Section 4, we review the company sentiment indicator methodology applied in this study. Section 5 evaluates the return predictability of the indicators generated from Dow Jones, Web, and the intersection of both versions under the framework of the short-term reversal model. Finally, in Section 6 we present our conclusions.
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.
RavenPack is introducing a multidimensional approach to news analytics that captures the evolving complexity of news, enabling traders to build more dynamic and transparent strategies.
New research using RavenPack Job Analytics to quantify tech adoption in hiring posts proves that companies hiring for novel tech skills outperform peers from an investment perspective.
Our multi-asset allocation strategy based on inflation nowcasts and RavenPack sentiment analytics outperforms the S&P 500 and stabilizes volatility. With real Sharpe ratios of up to 1.25 and a risk control approach, it delivers a compelling inflation hedge for investors.