A TEI@I-Based Integrated Framework for Port Logistics Forecasting
This paper proposes an integrated forecasting framework based on the TEI@I methodology for port logistics forecasting. The framework analyzes and forecasts the port logistics time series data with a few steps. Firstly, census X12 seasonal adjustment method is applied to decompose the time series to several components: trend and cycle component, irregular component and seasonal component. Secondly, econometrical models and artificial neural network techniques are used to forecast the trend and cycle component and irregular component respectively. Thirdly, event-study method and expert system technique are applied to evaluate the effects of economic and other events that may impact port logistics. Finally, synthetic forecasting results are obtained based on the integration of the predictions from three above steps. For illustration, Shenzhen port container throughout series is used for a case study. The empirical results show the effectiveness of the TFI@I-based integrated model for port logistics forecasting.
port logistics container throughput forecasting TEI@I methodology back-propagation neural network
Xin Tian Xiaoshan Lu Xingmai Deng
School of Management Graduate University of Chinese Academy of Sciences Beijing, 100190, China School of Economics and Management Bcihang University Beijing, 100191, China School of Management and Economic Beijing Institute of Technology Beijing, 100081, China
国际会议
北京
英文
293-296
2009-07-24（万方平台首次上网日期，不代表论文的发表时间）