Forecasting Tourism: A Sine Wave Time Series Regression Approach

Abstract

This article studies the use of an exponentially weighted nonlinear time series model to fit the tourist arrival data. A model which comprises a linear term in time and a sine function in time is employed. Because of the seasonal fluctuation in the data, deseasonalized data are used in fitting the model. The approach suggested is applied to the tourist arrival data in Singapore and the fitted model is then used to forecast the tourist arrivals. The proposed model is compared with the naive I model, the naive II model, a simple linear regression time series model, and an ARIMA model. Comparison of the mean absolute percentage errors shows that the proposed model is the best among all these models.