期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2017
卷号：9
期号：1
页码：14
出版社：International Center for Scientific Research and Studies
摘要：Due to the dynamically increasing importance of the tourismindustry worldwide, new approaches for tourism demand forecastingare constantly being explored especially in this Big Data era. Hence,the challenge lies in predicting accurate and timely forecast usingtourism arrival data to assist governments and policy makers to caterfor upcoming tourists. In this study, a modified Empirical ModeDecomposition (EMD) and Artificial Neural Network (ANN) modelis proposed. This new approach utilized intrinsic mode functions(IMF) produced via EMD by reconstructing some IMFs throughtrial and error method, which is referred to in this research asdecomposition. The decomposition and the remaining IMFcomponents are then predicted respectively using ANN model.Lastly, the forecasted results of each component are aggregated tocreate an ensemble forecast for the tourism time series. The dataapplied in this experiment are monthly tourist arrivals fromSingapore and Indonesia from the year 2000 to 2013 whereby theevaluations of the model’s performance are done using two wellknownmeasures; RMSE and MAPE. Based on the empirical results,the proposed model outperformed both the individual ANN andEMD-ANN models.
