A Seasonal ARIMA Model of Tourism Forecasting: The Case of Sri Lanka

Abstract

Many scholars have attempted to forecast the tourist arrival series in different countries. The aim of this paper is to find a suitable SARIMA model to forecast the international tourist arrival to Sri Lanka. Monthly data of tourist arrival from January 1995 to July 2016 is used for the analysis. Seasonality in the data series is identified using the HEGY test. The Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute percent Error (MAPE) are used to measure the forecasting accuracy. The result shows that the SARIMA (1, 0, 16) (36, 0, 24)₁₂ model is suitable to forecast the tourist arrival in Sri Lanka.

Keywords: Tourist Arrival, SARIMA model, HEGY test, Forecasting accuracy