Evaluation of the Performance of Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANNs) Models: Application to Confirmed Cases of Covid-19 in Nigeria

In this study, the performance of Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANNs) models was investigated evaluated using daily confirmed cases COVID-19 in Nigeria. The stationarity status data collected established Augmented Dickey Fuller unit root test. residual normality test also carried out with plots indicating adequacy fitted ARIMA model. results neural networks were analyzed back-propagation for multilayer feed-forward powered by sigmoid function. Utilizing backpropagation method based on three factors expressed terms learning rate, distance between actual output predicted activation function, network weights generated indices ANNs Mean Square Error (MSE), Root (RMSE) Absolute (MAE revealed that model performed better than ANN considering minimum prediction error forecasting ability. (2, 1, 1) appeared to be best over covid-19 considered.