以GARCH-ARMA探討日本來台旅遊預測

Japan Demand for Tourism in Taiwan

10.29938/TWTOURISM.200805.0203

丁誌魰(Chih-Wen Ting)；陳韋辰(Wei-Chen Chen)

觀光旅遊人數 ； 預測模式 ； 時間序列模式 ； Forecasting ； Time Series Models ； Tourism Industry

臺灣地方鄉鎮觀光產業發展與前瞻學術研討會論文集

2008年度（2008 / 05 / 01）

203 - 213

繁體中文

日本一直都是台灣外來旅遊的最重要客源。但是國際間的交流日益頻繁，觀光事業的競爭也愈來愈激烈，想在之中脫穎而出，唯有靠正確的決策和完善的規劃與管理。爲了達到這樣的目的，必須透過對於來台觀光旅客需求的精確預測，才能準確的掌握市場狀況，進而著手各種軟硬體設施的投資。而不適當的評估或是不精確的預測，將導致觀光資源不敷所需或閒置浪費。 本研究以1991年1月至2007年6月的日本來台觀光旅遊人數爲研究對象，共198筆資料，取前80%的資料來建構模式，後20%的資料來評估模型。預測39筆資料的MAPE值爲2.3%，而且準確的預測出日本來台旅遊人數的變化及未來趨勢，故本研究所建構出的單變量時間序列模型，具備很好的預測能力。

Japan has been the most important source that Taiwan travels all the time. But the international exchange is frequent day by day, the competition of the tour undertaking is fiercer and fiercer, only depend on correct decision and planning and management of perfection. In order to reach such an eye, must be through for coming to China to visit the accurate prediction of passenger's demand, could master the market situation accurately, and then set about the investment of different software and hardware facilities. The inappropriate assessment or not accurate prediction, will result in visiting resources and will not apply needing but leave the waste unused, absolutely not a competitor does. The number of people has come to China to go sightseeing as the research object with Japan from January of 1991 to June of 2007 in this research, amount to 198 materials , fetch the first 80% materials is it build way of constructing to come, the last 20% of the materials come to assess models. MAPE value of predicting 39 materials is 15.05%, and only predict 26 materials, MAPE value can drop to 9.82% , there is this that knows that this research institute builds the single variable time array model constructed out, have very good prediction ability.