Case Studies
RavenPack | February 18, 2015
US earnings season is drawing to a close it appears over two thirds of companies that have reported so far have beaten expectations.
Subsequently all geopolitical risks seem to have been ignored, apart from in passing conversation, and the S&P 500 has hit an all-time high.
Well, here’s another angle on earnings season . Figure 1 shows sentiment derived from earnings-related articles is only slightly higher than before earnings season on a three-month view - but it’s still only around the neutral mark and not as high as it was last earnings season. There’s also been a massive drop in our 14-day measure of sentiment in the last two weeks.
The chart shows the 90-day relative strength index of earnings-related sentiment (red line) against the 14-day RSI (black line). The blue bars denote the number of earnings events detected, aka, media attention.
I’m no technical analyst but one could say momentum is on the downside . Translated, it means that earnings-related events in the last two weeks were weaker, sentiment-wise, than those in the first three weeks of earnings season. We’ll need to wait for the remainder of earnings season to decide whether the slump in the short-term indicator continues, pulling longer-term sentiment lower, or not.
Taking a broader view across all news sentiment, the situation looks even worse over the short-term . Figure 2 shows the RavenPack 14-day sentiment momentum indicator reaching its lowest point in a year. But the longer-term indicator has not dipped in sympathy yet, so, again, we’ll need to see if that short-term indicator turns higher soon.
Elsewhere, figure 3 shows sentiment derived from US news related to Mergers & Acquisitions doesn’t look so good over both short and longer-term horizons.
On the plus side, however, US analysts are very positive . No surprise given the earnings season so far. See figure 4.
In conclusion, news sentiment is not supportive of the recent market highs but the euphoria of earnings season’s empirical result - and that there’s nothing else to invest in - may continue to buy equities.
The sentiment Relative Strength Indicators are produced by finding the novelty-weighted sum of all event sentiment concerning the company each day and then calculating traditional 14-day and 90-day RSIs of this sum.
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.