Analysis of COVID-19 Distribution in Countries Using Unsupervised Machine Learning

Although more than two years have passed since the spearing of COVID-19, a global pandemic, there are still major peaks in the number of confirmed cases and deaths. Although governments are trying to overcome this disease with different policies, it is not entirely controlled yet. In this study, two methods of unsupervised learning, K-Means and Hierarchical algorithms, were used to cluster 207 countries based on social, economic, and health characteristics. Thus, countries with similar factors can take proactive steps to control the pandemic. The optimal number of clusters was considered k=6 based on the elbow method. To obtain the most associated features, the correlation between selected variables and confirmed COVID-19 cases, deaths, and vaccination rates was analysed. The government stringency index showed a strong correlation with the number of vaccinations, whereas environmental health indicators were weakly correlated with mortality from COVID-19. Politicians can make better decisions by considering these indicators and therefore, manage the negative consequences of COVID-19.

Analysis of COVID-19 Distribution in Countries Using Unsupervised Machine Learning Keywords:

COVID-19 , Clustering methods , Unsupervised learning , K-Means , Hierarchical clustering