A0243
Title: On predicting growth factor of daily new cases data of COVID-19 epidemic in Italy using ARIMA-ANN hybrid model
Authors: Samir Safi - United Arab Emirates University (United Arab Emirates) [presenting]
Abstract: The Auto Regressive Integrated Moving Average, ARIMA model, cannot capture the nonlinear patterns exhibited by the 2019 coronavirus COVID-19 in terms of daily growth factor of daily new cases data in Spain. As a result, Artificial Neural Networks (ANNs) model is commonly used to resolve problems with nonlinear estimation. Different models that include ARIMA, ANNs, seasonal decomposition of time series, and a combination of these three models, hybrid model, were proposed to forecast the Growth Factor of COVID-19. The aim is to provide forecasting insights and criteria to use similar time series data to predict the growth factor of COVID-19 and to select the most suitable forecasting model for forecasting purposes. The best forecasting model selected was compared using the forecasting assessment criterion known as RMSE and MAE. The results add to the growing body of literature that seeks to accurately forecast the spread of COVID-19 by combining multiple models used by other researchers. The results are useful because it provides an accurate forecast for the growth factor of the COVID-19 epidemic. The importance of appropriate forecasts for policymakers to enhance better decision making is underscored.
