Evaluating the performance of countries in COVID-19 management: A data-driven decision-making and clustering

The COVID-19 outbreak, first reported in Wuhan, China, spread rapidly and endangered human lives and livelihoods globally. Researchers have utilized available tools and facilities to mitigate its impact across dimensions. In this study, we propose a comprehensive, data-driven framework to evaluate periodically 168 countries' performance, considering four distinct variable categories since the advent of COVID-19. We assess and leverage four clustering methods of K-means, Gaussian Mixture Model (GMM), Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and Spectral, as well as three Multi-Criteria Decision-Making (MCDM) approaches, including Combined Compromise Solution (COCOSO), Grey Relational Analysis (GRA), and Evaluation Based on Distance from Average Solution (EDAS) for ranking the countries. The results are analyzed thoroughly-among the examined factors, "Total Recovered", "GDP Per capita", and "Hospital Beds / 1 K" most critically impacted evaluating outcomes, while" Male Smokers", "Diabetes Prevalence", and "Cardiovascular Death Rate" are least influential. The novel metric "Medical Waste" also demonstrates more vital than 86 % of existing indicators. Moreover, the findings reveal associations between countries' development levels and their corresponding cluster assignments. For more precise analysis, we investigate the intra-cluster and inter-cluster approaches, each of which revealed countries' promotion or degradation regarding rankings within a cluster or transitions between clusters. Finally, appropriate policy-making and management strategies are presented to enhance countries' preparedness for potential future outbreaks based on the results.