| October 26, 2020
RavenPack uses Artificial Intelligence to analyze sentiment, media attention and historical voting patterns to predict the US presidential election next week. Our model has accurately predicted the winner in 4 out of the last 5 elections.
Biden is leading Trump as the race to the White House enters the final bend, with our election monitor projecting Biden to win by 307 electoral college votes (ECV) to Trump’s 231.
Minnesota and Nevada are 2 key marginal states that have swung to Trump in the last week but this was balanced out by a swing in projections for North Carolina to Biden, who is now 55.7% likely to take the state.
When official polling data and our projections agree they tend to provide the basis for a more confident forecast; likewise when they clash it can be a sign that polls may be out.
The monitor has a feature that automatically highlights states where there is non-confirmation between polling data and monitor projections by adding a cross-hatch. At the time of writing, Nevada, Minnesota, and Arizona are all key marginals showing disagreement. The same goes for the not so marginal seats of Iowa, Nebraska, and Georgia, as shown in the table below.
It is interesting to note that in all the states where there is non-confirmation Trump is shown as leading by the monitor and Biden by the polls.
Historically the monitor is the more accurate, which suggests all the states will probably fall to Trump. As such, this should not change the monitor’s overall projected outcome, and Biden should still probably win by a large margin - it will, however, indicate that polls may be overstating the extent of Biden’s popular support.
Biden is leading in 7 out of the 13 battleground states we regularly keep an eye on (see table below), Michigan, Wisconsin, Pennsylvania, Florida, New Hampshire, Maine, and North Carolina.
Trump meanwhile leads in Minnesota, Nevada, Arizona, Georgia, Ohio, and Texas.
The largest swings since our last update a week ago, have occurred in Nevada (+35.1% to Trump), North Carolina (+23.7 to Biden), and New Hampshire (-18.6 to Biden).
Best Regards - Team RavenPack
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.