 The study found that the autoregressive integrated moving average, ARIMA, model outperformed the extreme gradient boosting, XGBoost, model in predicting the number of COVID-19 confirmed cases and deaths in Bangladesh. This suggests that the ARIMA model may be more effective at accurately predicting the spread of a novel pandemic in Bangladesh and other countries with similar characteristics. This article was authored by M. D. Siddhika Rahman, Armin Hossain Chowdhury, and Mifta Huzannat Amron.