以單變量ARIMA模式、類神經網路、灰色GM(1,1)模型預測高雄港貨櫃吞吐量
Prediction of Container Throughput in Kaohsiung Port Using Univariate ARIMA, Neural Network, and GM (1,1) Models
國立高雄大學資訊管理學系(Department of Information Management, National University of Kaohsiung);樹德科技大學經營管理研究所(Graduate School of Business and Administration, Shu-Te University)
摘要
貨櫃吞吐量對台灣經濟扮演著舉足輕重的角色,且能帶動國家整體的經濟發展,因此建構未來貨櫃吞吐量需求模型,以提供足夠的資訊,做為政策研擬及港埠發展規劃之用,為當前重要的課題。本研究以單變量ARIMA模式、類神經網路及灰色GM(1,1)模型三種預測模型應用於高雄港貨櫃吞吐量之預測,且透過MAPE、RMSPE與THEIL三種評鑑指標加以評估其效能。研究結果顯示各預測模型均有高度之精準度,其中又以灰色GM(1,1)模型有最佳的適配能力,其次為單變量ARIMA模式,最後為類神經網路。
Abstract
The container throughput plays an important role in Taiwanese economic and it is able to enhance national economic development. To provide the sufficient information for policy making and development planning of ports, building the future demand model of container throughput is a very important issue. This study uses univariate ARIMA, neural network, and GM (1,1) models to predict the container throughput in Kaohsiung port and uses MAPE, RMSPE and THEIL evaluation index to evaluate their efficacy. The analytical results show the predicting models are with high accuracy. The GM(1,1) model is the best for predicting container throughput, followed by univariate ARIMA and neural network.
關鍵詞
- 類型
- 論文
- 期刊
- 臺大管理論叢
- ISSN
- 1018-1601
- 卷期
- 17卷2期
- 出版
- 2007年06月
- 頁碼
- 107–132
- 編號
- NTUEJ00010302
同期目錄
- 隨機模式下保險公司盈餘管理:情境基礎資産配置策略邱嘉洲(Chia-Chou Chiu);李賢源(Shyan-Yuan Lee)・頁 001–040
- 考慮極値與VaR限制之最適資產配置顔錫銘(Simon H. Yen);李美杏(Mei-Hsing Lee)・頁 041–068
- 勞退新制的最適資產配置、所得替代率與保證成本繆震宇(Jerry C. Y. Miao)・頁 069–090
- 確定提撥制下退休基金之最適提撥率與最適資產配置黃泓智(Hong-Chih Huang)・頁 091–106
- 以單變量ARIMA模式、類神經網路、灰色GM(1,1)模型預測高雄港貨櫃吞吐量郭英峰(Ying-Feng Kuo);陳邦誠(Pang-Cheng Chen)・頁 107–132
- 顧客價值遷移路徑分析:馬可夫鏈模型任立中(Li-Chung Jen);陳靜怡(Ching-I Chen)・頁 133–158
- 創造力人格、領導型態與績效關係之探討王精文(Ching-Wen Wang);徐碧慧(Pi-Hui Hsu);李珍玫(Chen-Mei Li)・頁 159–182
- 甄選面談中外表與性別偏誤之探討:結構式面談能消除它們嗎?陳建丞(Chien-Cheng Chen)・頁 183–208