Open AccessForecasting ASEAN Tourist Arrivals in Malaysia Using Different Time Series Models
Author(s) -
Ali Rafidah,
Ernie Mazuin,
Ani Shabri
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1101.0986s319
Subject(s) - autoregressive integrated moving average , support vector machine , mean squared error , mean absolute percentage error , autoregressive model , hilbert–huang transform , series (stratigraphy) , computer science , statistics , time series , artificial intelligence , econometrics , machine learning , mathematics , paleontology , white noise , biology
In this study three time series models are used for forecasting monthly ASEAN tourist arrivals in Malaysia from January 1999 to December 2015. Brunei, Thailand and Vietnam of ASEAN country selected as case study. This paper compares the forecasting accuracy of seasonal autoregressive integrated moving average (SARIMA), Support Vector Machine (SVM) and Wavelet Support Vector Machine (WSVM) and Empirical Mode Decomposition with Wavelet Support Vector Machine (EMD_WSVM) using root mean square error (RMSE) and mean absolute percentage error (MAPE) criterion. Moreover, correlation test has also been carried out to strengthen decisions, and to check accuracy of various forecasting models. Based on the forecasting performance of all four models, hybrid model SARIMA and EMD_WSVM are found to be best models as compare to single model SVM and hybrid model WSVM.