Multi-country analysis of the COVID-19 pandemic typology using machine learning and neural network algorithms

Abstract

The paper presents the results of a multi-country analysis of the intensity typology of the COVID-19 pandemic in 30 countries of the European region based on publicly available and regularly updated panel data for the entire period 2020-2022 of high pandemic activity. In the generated space of classification features, using cluster analysis algorithms, all countries are divided into three classes, which differ in the intensity of the epidemic process. Based on the obtained country ratings, an integral statistical indicator of the COVID-19 pandemic is constructed. A set of discriminant analysis machine learning and neural network algorithms are used to estimate current as well predict the expected class of the epidemic state based on the newly acquiring data.