| April 13, 2020
A recent paper by Wolfe Research reveals how high-impact developments around volatile events, such as the coronavirus pandemic, can be quantified systematically using sentiment data, and applied in financial market forecasting.
In a topical report published on February 29th, Wolfe Research used RavenPack analytics to quantify the extent and direction of the COVID-19 outbreak, and to construct uncertainty and sentiment indices for at-risk countries. The report looks at the resulting change in analyst sentiment and the impact on various sectors across major markets, and shows how sentiment indices can be used to estimate the beta sensitivities to the epidemic event.
The Wolfe team employed RavenPack’s keyword search functionality to isolate coronavirus-linked news and filter the remaining articles based on health-related events by country. The final screen included only fact-based stories that were highly relevant and novel. The dataset was used to create two daily indices that track coronavirus uncertainty and sentiment.
The paper showcases analyst revisions of sales and earnings estimates in major markets by sector, and finds that China and the US seem to be somewhat complacent, while the analysts appear to be more pessimistic in Japan and rest of Asia.
To tie their findings around the revisions’ data to market reactions, the Wolfe team performed a set of event studies to analyze the overall price impact by sector, and found that standard defensives, such as utilities, real estate and telcos in the US outperformed the market significantly whenever there was a sudden dip in virus sentiment. On the other hand, energy, transportation and semiconductors tended to underperform (although Russia/Saudi events likely had a more substantial role to play in energy).
Finally, the paper used the COVID-19 sentiment indices to estimate the beta sensitivity of each asset and sector to the epidemic event. They showed that in the US, energy, transportation, and materials were the most negatively exposed to the coronavirus sentiment, while the telcos, technology hardware, food/beverage/tobacco, and real estate sectors appeared to be the most defensive. In a similar fashion, they included a list with a subset of stocks that showed the most sensitivity to sentiment surrounding the epidemic.
The key takeaway from the report was that high-impact developments around volatile events, such as the 2020 coronavirus pandemic, can be quantified systematically using sentiment data, and used for assessing the direction and intensity of market moves surrounding the prevailing socio-economic fears.
where we are pulling together all our analytics, information and insights about the novel coronavirus.
Please use your business email. If you don't have one, please email us at email@example.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 firstname.lastname@example.org. For more information, you can
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.