Our recent data science study about calendar earnings changes and news sentiment shows evidence of alpha generation.
When companies change the dates of their official earnings releases it has been speculated that it is because they want to delay the release of bad news or bring forward the release date for good news.
In a recent white paper, RavenPack data scientists sought to test this hypothesis by constructing strategies that bought and sold stocks when companies changed their earnings dates. Read the full study here.
Below are some of the report’s key findings:
- Portfolio investment strategies that bought after advances, and sold after delays, produced annual excess returns of 8.4%, for portfolios of mid to large-cap stocks and 18.6% for small-caps.
- Adding a news sentiment overlay was effective at highlighting sell candidates, especially in an environment of positive sentiment; here the negative surprise factor from a delay led to an average 50 negative basis point stock decline over 20 days.
- Overlaying with sentiment specifically from earnings associated news and altering portfolio weightings to reflect this, led to an even more profitable strategy, that generated annual excess returns of 10.5% for mid and large-cap stocks and 26.7% for small-caps.
The graph below shows the market drift following earnings announcements for different earnings calendar date change scenarios under differing sentiment conditions.You can easily implement the results of this white paper using the RavenPack Analytics platform which tracks over half a million entities using 22,000 different news sources and now includes the RavenPack Earnings Dates dataset, containing changes in the earnings calendar from 2006 for more than 9,000 listed companies.
Request the full White Paper here: Trading Around the Earnings Call
Compliments of RavenPack – a member of the EACCNY.