Prediction of dengue outbreak: a comparison between ARIMA and holt-winters methods / Norwaziah Mahmud ... [et al.]

Dengue is a globally known infection in which the virus is transmitted by mosquitoes and can lead to death. Selangor has been reported to have the highest incidence of dengue infections among the communities in Malaysia. There is currently a new pandemic, COVID-19, which occurred worldwide, including Selangor, which led to this study on the pattern of dengue cases during COVID-19. The aim of this study is to develop the best model to predict the future value of dengue cases in Selangor. In order to meet the objectives, the ARIMA method and the Holt-Winters method were used to evaluate dengue case data collected in Selangor. The best model was chosen by evaluating the Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Percent Error (MAPE) measurement errors. Then, the forecasted number of dengue cases was calculated using the best model generated. The best model to forecast dengue cases in Selangor is the Additive Holt-Winters model since it showed the lowest values of all measurement errors compared to the Multiplicative Holt-Winters and ARIMA (1,1,0) models.