India confronted a serious challenge in the initial throes of the COVID-19 pandemic. This study addressed this by leveraging machine learning to analyse confirmed cases and support better decision-making. We compared the efficacy of Auto-Regressive Integrated Moving Average (ARIMA), Facebook Prophet and Long Short-Term Memory (LSTM) models on a Kaggle dataset, visualizing the results with Power BI to forecast future trends. The LSTM model, evaluated using Mean Absolute Percentage Error (MAPE), demonstrated superior accuracy in predicting case numbers. This research underlines the importance of data analysis during public health emergencies. Machine learning offers valuable insights for policymakers, empowering them to control outbreaks and allocate resources effectively. Ultimately, this paves the way for strengthened public health responses and preparedness for future pandemics.