How Would News Sentiment Strategies Have Performed During the Corona Crisis Compared to Broker Research?

July 20, 2020

A recent study ranked over 150 brokers according to how profitable their research recommendations would have been during COVID - and they included signals based on RavenPack data.

The difficult market conditions that characterized the first quarter of 2020 due to the COVID crisis raise the question of how well research recommendations would have performed during the period. To add signals based on news sentiment data into the mix might further add an interesting alternative data twist to the conundrum.

This was exactly what Invisage, a multi-asset research evaluation firm set out to investigate in a recent report entitled “Why is Research Evaluation Important and How Can Technology Help”.

Why is Research Evaluation Important and How Can Technology Help

Invisage analyzed the research recommendations produced by 150+ brokers in the period from February 1 to June 15 to see how well they would have performed if implemented. They also included signals from their own Invisage Sentiment indicator, built using RavenPack data.

The sample included a total of 16,850 stock trading recommendations in sectors as diverse as Basic Materials, Healthcare, and Technology. Only research in U.S. equities was included.

The results from the evaluation report show that a third of all brokers (32.76%) produced a positive return during the period, and three out of four firms (74.14%) outperformed the S&P500, which declined -5.61% in the same period.

The *Invisage Sentiment signals, using RavenPack data, performed relatively well, ranking 4th against a list of brokers providing research and generating a 16.82% hypothetical return, which when considering the large sample size of over 6800 recommendations was a robust result.

Invisage Sentiment signals


Invisage says its research is aimed at using smart technology to provide investors with more refined consumption, so as to aid them in distilling the best investment ideas for generating alpha.

To develop signals such as those in the above study subscribe to the RavenPack Analytics Platform, which includes sentiment data on over 300 thousand individual entities and events, available via dashboards or our web APIs.



By providing your personal information and submitting your details, you acknowledge that you have read, understood, and agreed to our Privacy Statement and you accept our Terms and Conditions. We will handle your personal information in compliance with our Privacy Statement. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability, and objection by emailing us at privacy@ravenpack.com in accordance with the GDPRs. You also are agreeing to receive occasional updates and communications from RavenPack about resources, events, products, or services that may be of interest to you.

Data Insights

Read More