Towards Effective Pandemic Management: Analytic Network Process Framework for Assessing Country Responses to COVID-19

The COVID-19 pandemic has drastically reshaped global societies, presenting unprecedented challenges to public health systems and governance. Performance evaluation among countries is crucial to identify effective strategies and improve responses to such global crises. This study aims to provide policymakers with a comprehensive framework for evaluating and improving pandemic management strategies across countries. By integrating Machine Learning (ML) and Multi-Criteria Decision Making (MCDM) techniques, we developed a novel approach that considers both the interconnections between evaluation criteria and the mutual impact of countries on one another. The study employs the Analytic Network Process (ANP) to assess the performance of countries, leveraging diverse factors such as healthcare infrastructure, economic status, demographic characteristics, and public health measures. The Entropy method is used for feature weighting, while hierarchical clustering aids in pattern identification. Our findings reveal that a multifaceted approach encompassing widespread testing, mortality reduction, economic support, and healthcare infrastructure investment is critical for effective pandemic management. The results underscore the importance of tailored public health strategies that protect vulnerable populations and promote comprehensive public health measures. By focusing on these key areas, policymakers can create robust roadmaps for managing current and future pandemics, ensuring more effective and resilient responses.