Time Series Analysis to Predict COVID 19 Mortality in the United States

Current research has been performed as an un­dergraduate thesis at Hollins University. The goal of this research is to perform time se­ries analysis on COVID-19 daily new cases in the United States using the Auto Regressive Integrated Moving Average (ARIMA) model. We explore the reasonability of the predictive model. We divided our model into test and training set and then later compared our predictions with the test data. We used measures such as Mean Absolute Error, Root Mean Squared Error and, Mean Absolute Percent­age Error to check the validity of our model. We observed that the predictions do not seem to fluc­tuate a lot as the actual values do