• For anyone interested, the data scientist Guyang Yu ( Twitter | LinkedIn ) has created a remarkably accurate adaptive model of the COVID-19 pandemic. You can view projections by country or state-by-state. It’s based on the SEIR/SEIS model using the daily death total provided by Johns Hopkins’ CSSE to simulate the COVID-19 epidemic in each region. The parameters/inputs of this simulator are then incorporated using machine learning techniques that attempt to minimize the error between the projected outputs and the actual results. It’s one of the models the CDC now uses, and a terrific solo effort worth following.
