Although the official number of deaths caused by covid-19 is now 7m, our single best estimate is that the actual toll is 27.1m people. We find that there is a 95% chance that the true value lies between 17.9m and 32.9m additional deaths.
The way they explain their model is pretty impressive as a news organization. They even shared their software: https://github.com/TheEconomist/covid-19-the-economist-global-excess-deaths-model
I didn’t really understand why they chose that particular machine learning algorithm and how acceptable their test on the model was, though. Well, doing that would require a scholarly quality research article with lots of lots of tables, so, I can’t complain…
But… maybe, if they make a surprising if not outlandish claim like this I wish to see more on the analysis before I believe them.