Exploring Global Variations in News Impact on Equities

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.

• On average, US companies tend to have higher news coverage than European and Emerging markets in both the Dow Jones and Web Editions.
• Novel news events are more evenly distributed across US stocks compared to European and Emerging Market stocks.
• Compared to the Dow Jones Edition, web content is more tilted towards US stocks.
• The news signal has strongest impact on European markets. Based on sentiment data from the combined Editions of Dow Jones and Web news analytics, with holding period of 2 trading days and 10 bps transaction cost, the European portfolio yields an Information Ratio of 2.53 and a Hit Ratio of 62.4%.

Exploring Global Variations in News Impact on Equities [White Paper]

Introduction

We have previously shown how both the Dow Jones and Web Editions of RavenPack News Analytics contain valuable information that can help predict future stock returns for the US market, as represented by the Russell 3000 (Hafez and Xie, 2014). In this study, we extend our previous work to compare the U.S., Europe and Emerging Markets.

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.

Data Description

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.