SARIMA and Exponential Smoothing model for forecasting ecotourism demand: A case study in National Park Kuala Tahan, Pahang

Abstract

Abstract Tourism forecasting can lead to an important element in tourism industry to ensure that each investment by individuals, companies and government is profitable. From economy perspective, eco-tourism is a growing business, and it is an important indicator to the tourism industry. It also generates income revenue to the owner and surrounding communities. This research aims to forecast the eco-tourism demand based on number of tourist arrival for both local and foreign tourist at National Park Kuala Tahan, Pahang. The forecasting models used are seasonal autoregressive integrated moving average (SARIMA) and exponential smoothing. Both forecasting models are compared and assessed using mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE). The result demonstrated that SARIMA (1,0,0)(1,0,1)12 the best model to forecast the number of tourist arrival in National Park Kuala Tahan, Pahang is which give the smallest forecast evaluation values. Hence, the exponential smoothing is not as good as the SARIMA model in forecasting tourist arrival for the data used. In future study, SARIMA model can be used to compare the local and foreign tourist arrival for eco-tourism destination.