Identification of Patterns of Development of the Incidence of COVID-19 in OECD Countries Using Cluster Analysis

Filimonov, V.; Kulikova, O.; Usacheva, E.; Shmyga, I.

Background: The development of the incidence of COVID-19 in the OECD countries is characterized by strong variability and heterogeneity, which determines their different impact on the economies of these countries. The purpose of the study is to identify patterns in temporal trends in the incidence of COVID-19 in 37 economically developed countries, as well as in Russia and China. Methods and results: The research was carried out on the basis of data from the sites 'Our World in Data' and the International Monetary Fund. To solve the problem of grouping countries according to the COVID-19 development trend, the k-means cluster analysis method was used in combination with the DTW algorithm. Calculations were performed using Python 3.7. As a result, 6 clusters were identified in the OECD countries. Russia and China are not close to any of them in terms of the parameters characterizing the profiles of the clusters. In Russia, with the lowest number of cases at the beginning of the analyzed period, there is an average growth rate, against which the average level of the number of cases will be reached by the end of 2020. In China, with the highest incidence of cases at the beginning of the analyzed period during 2020, there was the lowest growth rate, due to which at the end of the analyzed period China had the lowest number of cases. Conclusions: Our research provided a new basis for describing, interpreting and predicting the development of COVID-19 in economically developed countries. © 2021 IEEE.