A dynamic decision support system to tackle the spread of COVID-19: predictive and clustering approaches

This study proposes a novel Dynamic Decision Support System (DDSS) framework aimed at enhancing countries' pandemic preparedness through robust forecasting and adaptive clustering analysis of Coronavirus Disease 2019 (COVID-19) data. The forecasting module integrates multiple Machine Learning (ML) models with a recursive error-adjustment mechanism that significantly improves long-term prediction accuracy of cumulative COVID-19 cases compared to conventional time series models such as Autoregressive Integrated Moving Average (ARIMA), Error Trend Seasonality (ETS), and Long Short-Term Memory (LSTM). The clustering component performs a dynamic, year-over-year classification of countries based on health, policy, and socio-economic indicators. By employing K-means clustering and Multi-Attribute Decision-Making (MADM) techniques, the study evaluates changes in countries' pandemic performance over time and identifies the stringency index as a critical determinant influencing cluster shifts. The proposed framework not only reveals performance trajectories and degradation risks for individual countries but also provides a structured data-driven basis for strategic policymaking. Notably, the analysis demonstrates how relaxing governmental measures, despite high vaccination rates, can adversely affect country classification, highlighting the indispensable role of strict interventions. This integrated approach, combining adaptive ML forecasting with temporal clustering and interpretability via Shapley Additive explanations (SHAP) analysis, provides a dynamic and practical decision-support framework for pandemic response.