The Handbook of News Analytics in Finance

8.7 SUMMARY AND DISCUSSIONS

We began this article by highlighting that the earnings revisions strategies that the majority of investors employ typically do not identify the piece of information that has triggered the change in forecasts. Our aim has been to understand what type of information causes analysts to revise their earnings expectations, how the informational content of the signal varies according to the news catalyst, and whether investors can use news flow signals as input to their models. We have shown that there is a hierarchy to the informational content of news and that investors can gain an advantage by using news flow to trade ahead of analyst revisions.

Our initial analysis on news flow has since stemmed into a variety of research projects. With over 80% of corporate data estimated to be unstructured (the most common unstructured data is text), this is a growing area of research. With data vendors dedicating greater resources to the collection and analysis of news flow, there is no reason for research to be limited to traditional corporate events such as earnings and trading updates. Data vendors and researchers are able to scour through internet blogs, social network sites, and Google Trends to find novel sources of information.

One of the perhaps surprising results from our earlier analysis in Section 8.4 is that there is no serial correlation in corporate news. Companies are equally likely to report good and bad news going forward. Since undertaking this initial ...