Big Data Case Studies
RavenPack | June 17, 2020
What caused the recent market meltdown? The media has argued that the Coronavirus “second wave” fears are most responsible for the drawdown (hardest hit on June 11th).
We looked at the media coverage signals and found that the “second wave” news volume drumbeat peaked on June 11th, around the NY market open.
While this factoid may appear to support the notion that the “second wave” theme was the obvious catalyst, we do not see a clear trend when observing it over a longer period; the peak, in truth, appears rather contemporaneous, with full history suggesting that this stand-alone signal should be interpreted with caution.
In reality, there are likely multiple factors that contributed to the selloff. The United States economy has officially entered a recession, with 2020 earnings estimated to be down 20% for the year . Yet, the S&P 500 has experienced a V-shaped recovery.
This doesn’t necessarily mean that the market has decoupled from the underlying market fundamentals, however. Rather, it suggests that the investors have largely written off 2020 and are focusing on the recovery in 2021 and beyond, with some estimates calling for a 30% increase in next year’s earnings. Of course, it is quite difficult to predict quarterly earnings, let alone any results a year from now.
This sets us up with an interesting dynamic, whereby uncertainty plays an outsized role, given the extended time interval, acting as a fulcrum. The market has set itself up to expect an optimistic set of scenarios next year, if not a full V-shaped economic recovery. This optimism is also reflected in the more positive news sentiment around U.S. employment, which does not align well with the official unemployment estimates just yet, although it does reflect much better than expected figures.
Any data suggesting that the recovery might take a longer time to materialize and that market optimism could, therefore, be misplaced, will have an outsized effect on price action.
To conclude, we can safely infer that the recent surge of second wave fears may have been the trigger for the significant market drawdown starting on June 11th, but that the underlying reasons may be more nuanced. For example, another factor could be signs of a negative sentiment trend forming within U.S. corporate events (equity actions, analyst ratings, price targets, revenues, earnings, acquisition & mergers, insider trading etc.) in the preceding days.
The pronounced negative trend started around June 8th, just a few days before the June 11th selloff. Looking at a longer timeframe, there was no other clear shift in the overall U.S. corporate sentiment trend since the beginning of February, days before the Coronavirus crisis started. This inflection may suggest that other underlying factors may have set the stage for the broader selloff.
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.