WSEAS Transactions on Mathematics
Print ISSN: 1109-2769, E-ISSN: 2224-2880
Volume 13, 2014
Forecasting with Fourier Residual Modified ARIMA Model - An Empirical Case of Inbound Tourism Demand in New Zealand
Authors: , , , ,
Abstract: Tourism, one of the gigantic industries in a country, has been considered as a complexly integrated and self-contained economic activity. Key determinants of the tourism demand have not been being fully identified in literature, so varied levels of the forecast accuracy existing in distinct formations of forecasting models, such as the autoregressive integrated moving average (ARIMA) and its joint Fourier modified model, are investigated in this paper. With a certain degree of Fourier-modification factors joined, the model performance is found to be significantly boosted. In an empirical study for the inbound-tourism demand forecasting in New Zealand, the Fourier-modified seasonal ARIMA model, named FSARIMA(1 ; 0 ; 1 )(1 ; 1 ; 1 )12 , is highly recommended due to its satisfactory forecasting power for the historical data. We further employ this model to provide the New Zealand’s tourism projecting demand in 2013 so as to assist policy makers as well as related organizations in early establishing their appropriate strategies for sustaining growth in this extremely-intensified competitive industry.
Search Articles
Keywords: ARIMA model, Tourism demand, Fourier modification, New Zealand tourism, Tourism forecasting
Pages: 12-21
WSEAS Transactions on Mathematics, ISSN / E-ISSN: 1109-2769 / 2224-2880, Volume 13, 2014, Art. #2