Harnessing Advanced Machine Learning for Predictive Modeling and Granular Analysis of COVID-19 Epidemic Dynamics

The precise forecasting of epidemic trends is essential for effective public health responses and resource allocation. This study investigates the application of machine learning techniques to predict the spread of COVID-19, leveraging a combination of the SIR model, linear regression, logistic curve fitting, and ARIMA. We implemented these models on global COVID-19 data to estimate the number of cases over time. Among the strategies tested, linear regression emerged as the most effective, demonstrating superior accuracy in identifying trends compared to the SIR model, logistic curve fitting, and ARIMA. The results highlight the potential of linear regression in epidemic forecasting, providing valuable insights for policymakers and health professionals. Future work could further enhance prediction accuracy by incorporating additional data sources and refining model parameters.