A data scientist’s projections of Covid-19 from here on out

It’s a model. From independent data scientist Youyang Gu. Real world has tracked his past model projections well.

Update Feb 24: He’s featured in Bloomberg as the single individual whose models have been better than the pros. He’s an engineer, not an epiastrologist. From the quotes in the story, Christopher Murray, MD, PhD at the UW’s IHME random number generation center remains blinded by his own brilliance.


  • The US will be near COVID-19 herd immunity by summer 2021 (Jun-Aug 2021). At a high level, herd immunity is a concept in which a population can be protected from a virus if enough people possess immunity. Current accepted estimates for the herd immunity threshold range from 60-90% of the population.
  • Due to vaccine hesitancy and the later arrival of a children’s vaccine, it is possible that we do not reach the levels required for herd immunity in 2021. Nevertheless, herd immunity is not a hard threshold, and being close to herd immunity may be sufficient to prevent large outbreaks.
  • At the time herd immunity is near, roughly half of the immunity will be achieved through natural infection, and the other half will be achieved through vaccination.
  • New infections may become minimal before herd immunity is reached. But due to imported cases and localized clusters, it is unlikely that new infections will drop to zero until at least 2022.
  • Deaths may drop to low levels even earlier (May-Jul 2021), in part due to a vaccine distribution strategy that initially prioritizes high-risk individuals. Once deaths fall to minimal levels, we may see a relaxation of restrictions.
  • Summarizing the above findings, our best estimate of a “return to normal” in the US is mid-summer 2021 (June/July 2021).
  • We estimate roughly 60-75% of the US population (~225 million) will receive at least one dose of the vaccine by the end of 2021, with children being the last group to receive it (starting in summer 2021 or later).
  • We estimate around 30-35% of the US population (100-120 million) will have been infected by the SARS-CoV-2 virus by the end of 2021. That is an additional ~50 million infections since mid-December 2020.
  • This translates to a final US COVID-19 death toll of roughly 600,000 (±100,000) reported deaths by end of 2021, or ~300,000 additional deaths since mid-December 2020.

Source: Path to Herd Immunity – COVID-19 Vaccine Projections | COVID-19 Projections Using Machine Learning

This chart is some what hard to read. The purple dotted line at bottom is the actual and projected daily new positive test cases. The top chart attempts to show the number of infections versus number of vaccinations. I think the reason the unusual presentation is indicating that some of the infected are also becoming some of the vaccinated, but I am not sure.

Leave a Reply

Your email address will not be published. Required fields are marked *