Amade2233/Forecasting-Covid-19-Mortality-Rate-in-West-Africa

# Forecasting-Covid-19-Mortality-Rate-in-West-Africa ## ABSTRACT #### COVID-19, a new acute respiratory disease, has hit the planet since 2019, killing millions and affecting the economy, politics, and civilization. As a result, an accurate prediction of COVID-19's mortality becomes critical in such a circumstance. Four different models were investigated in this comparative study, Hence, these include two classical time series models focusing on the Autoregressive Integrated Moving Average (ARIMA) model, the PROPHET model, and two Machine Learning (ML) models focusing on Random Forest (RF) model, and the Light Gradient Boosting Machine model. This study sets to determine which has the best performance when predicting the future case trends of COVID-19 in West African countries. However, After the collection of publicly available COVID-19 case data from the Johns Hopkins University Center for Systems Science and Engineering database, repeated experiments were carried out that used the data to forecast future trends for all models. Nevertheless, The Mean Squared Error (MSE) measure is then used to assess performance. The results reveal that the ARIMA model has the highest overall performance for all nations with exceptionally low MSE. Hence, making the ARIMA model the champion model for forecasting. Nonetheless, as a result, in comparison to the PROPHET, RF, and LGBM, the statistical model ARIMA performed better for forecasting COVID-19 mortality rate. Nigeria was also discovered to have the highest mortality rate in West Africa. This study demonstrates the great accuracy of the ARIMA model, which can be used to anticipate the spread of COVID-19 so that West African countries and their various government authorities may be more prepared and alert when managing the spread in a long/short run. ## Links ##### csse_covid_19_daily_reports ##### West Africa Covid-19 Mortality Prediction Web App ##### Amade2233/MYPROJECT (github.com)