Forecasting of COVID-19 dynamics in EU using randomized machine learning applied to dynamic models

The work is devoted to application of the theory of Randomized Machine Learning to forecasting of the COVID-19 pandemic based on SIR epidemiological model. We propose two modelling variants, the first is based on estimation of SIR model using real case data, the second is based on the idea of modelling transmission coefficient and its prediction. Comparative study of proposed approach is based on a comparison with the standard least squares approach and is carried out on a dataset of several countries of the European Union. It is shown the performance of the proposed approach and its effectiveness and adequacy under conditions of small amount of data with a high level of uncertainty.