Time Series Based Forecasting Model for Covid-19 in Different Countries

In the rapidly changing COVID-19 pandemic, accurate forecasting of confirmed cases, fatalities, and recoveries is crucial to strategic planning and implementation of public health actions. However, forecasting is complicated by the requirement for significant historical data and the unpredictability of the future. This study examines how data reliability, external variables, and social views affect forecasting accuracy. Since 2019, COVID-19 has grown globally, requiring aggressive measures without a cure. This research attempts to create a deep learning model that forecasts future trends using all available data to influence community safety decisions. Forecasting new diseases, deaths, and immunization rates is the main focus. The study carefully analyzes temporal sequences from three countries' COVID-19 data. The model uses two Simple RNN layers and three dense layers trained for 100 Adam optimizer iterations. The results reveal the pandemic's dynamic nature, informing effective public health measures.