Big Data NLP Election
RavenPack | August 05, 2020
ADP employment change rose by 167k in July; Decline in sentiment for Trump often precedes macroeconomic misses. Could investors have foreseen the miss? Read more below.
Despite showing a rise of 167k new jobs, July’s ADP employment report came in sharply below the above 1 million expected by economists. Could investors have foreseen the miss? We find that a bigger than usual deterioration in sentiment for Donald Trump often precedes macroeconomic misforecasts, and today’s data was no exception as Trump’s sentiment had been falling sharply over the last week.
“News sentiment towards Trump is directly positively related to the state of the economy. Some of the chatter about Trump that happens during the week before a key economic release will be about that release and therefore positive/negative views expressed on that release (including opinions about whether or not the release is likely to surprise consensus expectations and in what direction) will be contributing to the Trump sentiment captured by RavenPack.” Says Inna Grinis, Senior Data Scientist at RavenPack. “This is a good occasion to illustrate the advantage of news analytics vs traditional surveys. Consensus estimates are gathered by asking a number of economists with different forecasting accuracy for their predictions of key data releases at different points in time. By contrast, the sentiment expressed in the news the week before the release would incorporate the latest information available on the state of the economy and could therefore be a more timely and accurate predictor of the actual data release. This is something our Quant Research Team at RavenPack is exploring further.”
“News sentiment towards Trump is directly positively related to the state of the economy. Some of the chatter about Trump that happens during the week before a key economic release will be about that release and therefore positive/negative views expressed on that release (including opinions about whether or not the release is likely to surprise consensus expectations and in what direction) will be contributing to the Trump sentiment captured by RavenPack.” Says Inna Grinis, Senior Data Scientist at RavenPack.
“This is a good occasion to illustrate the advantage of news analytics vs traditional surveys. Consensus estimates are gathered by asking a number of economists with different forecasting accuracy for their predictions of key data releases at different points in time. By contrast, the sentiment expressed in the news the week before the release would incorporate the latest information available on the state of the economy and could therefore be a more timely and accurate predictor of the actual data release. This is something our Quant Research Team at RavenPack is exploring further.”
To find out more about how your organization can benefit from RavenPack data or to generate more meaningful macroeconomic insights - as in the example above - request a free trial.
The RavenPack Analytics Platform scans over 20,000 news sources to derive sentiment data on over 250,000 individual entities, tracking 6,800 different market-moving events, it is available on visual dashboards or via web APIs.
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.