基于因子分析和曲线拟合的集装箱吞吐量预测
|
摘要
为提高集装箱吞吐量的预测精度,提出基于因子分析和曲线拟合的集装箱吞吐量预测模型。以上海港为例,通过因子分析,分析影响集装箱吞吐量的主要因素,筛选出主因子,得到不同年份的综合经济发展值;再运用曲线拟合方法,建立以综合经济发展值为自变量,以集装箱吞吐量为因变量的三次曲线模型;运用自回归积分移动平均(autoregressive integrated moving average,ARIMA)模型预测2016—2020年的综合经济发展值,进而求得2016—2020年上海港集装箱吞吐量预测值。结果表明:该模型的拟合效果和预测精度均较高,可以运用到集装箱吞吐量预测中。给出上海港在国内经济新常态下转型升级的建议。
In order to improve the prediction accuracy of container throughput,a container throughput prodiction model based on factor analysis and curve fitting is proposed. Shanghai Port is taken as an example. Through factor analysis,the main factors affecting the container throughput are analyzed,the principal component factors are selected,and the comprehensive economic development values of different years are obtained; a curve fitting method is used to establish a cubic curve model,where the comprehensive economic development value is taken as an independent variable and the container throughput is taken as a dependent variable; the comprehensive economic development values of 2016-2020 are predicted by the autoregressive integrated moving average( ARIMA) model,thus the predicted values of the container throughput of Shanghai Port in 2016-2020 are obtained. The results show that the fitting effect and the prediction accuracy of the model are both high and can be applied to the container throughput prediction. The suggestions of the transformation and upgrading of Shanghai Port under the new normal of Chinese economy are given.
In order to improve the prediction accuracy of container throughput,a container throughput prodiction model based on factor analysis and curve fitting is proposed. Shanghai Port is taken as an example. Through factor analysis,the main factors affecting the container throughput are analyzed,the principal component factors are selected,and the comprehensive economic development values of different years are obtained; a curve fitting method is used to establish a cubic curve model,where the comprehensive economic development value is taken as an independent variable and the container throughput is taken as a dependent variable; the comprehensive economic development values of 2016-2020 are predicted by the autoregressive integrated moving average( ARIMA) model,thus the predicted values of the container throughput of Shanghai Port in 2016-2020 are obtained. The results show that the fitting effect and the prediction accuracy of the model are both high and can be applied to the container throughput prediction. The suggestions of the transformation and upgrading of Shanghai Port under the new normal of Chinese economy are given.
引文
[1]江舰,王海燕,杨赞.集装箱吞吐量及主要影响因素的计量经济分析[J].大连海事大学学报,2007,33(1):83-86.
[2]朱小檬,栾维新,朱义胜.基于时间序列-因果关系结合法的中国海港集装箱吞吐量中长期预测[J].大连海事大学学报(社会科学版),2014,13(5):1-5.
[3]王文.线性回归结合季节性复合序列的深圳港集装箱吞吐量预测[J].中国水运,2012,12(12):23-25,27.
[4]杨金花,杨艺.基于灰色模型的上海港集装箱吞吐量预测[J].上海海事大学学报,2014,35(2):28-32.
[5]陈昌源,戴冉,杨婷婷,等.基于改进GM(1,1)模型的上海港集装箱吞吐量预测[J].船海工程,2016,45(4):153-156.
[6]崔巍,叶佳.基于三次指数平滑的珠江内河集装箱吞吐量预测[J].珠江水运,2011(12):112-114.
[7]关克平,齐梦雅.基于指数平滑法的宁波舟山港港口吞吐量预测研究[J].中国水运,2013,13(12):28-29.
[8]范莹莹,余思勤.基于NARX神经网络的港口集装箱吞吐量预测[J].上海海事大学学报,2015,36(4):1-5. DOI:10. 13340/j. jsmu.2015. 04. 001.
[9]刘长俭,张庆年.基于时间序列BP神经网络的集装箱吞吐量动态预测[J].水运工程,2007(1):4-11.
[10]王再明,王宏波.灰色系统理论在港口吞吐量预测中的应用[J].武汉理工大学学报(交通科学与工程版),2005,29(3):456-459.
[11]陈秀瑛,古浩.灰色线性回归模型在港口吞吐量预测中的应用[J].水运工程,2010(5):89-92.
[12]徐国祥.统计预测和决策[M].上海:上海财经大学出版社,2006:202-216.
[13]王璐,王沁. SPSS统计分析基础、应用与实战精粹[M].北京:化学工业出版社,2012:230-256.
[14]陈羽. 2015年我国港口集装箱发展现状及趋势[J].中国港口,2016(4):48-53.
[2]朱小檬,栾维新,朱义胜.基于时间序列-因果关系结合法的中国海港集装箱吞吐量中长期预测[J].大连海事大学学报(社会科学版),2014,13(5):1-5.
[3]王文.线性回归结合季节性复合序列的深圳港集装箱吞吐量预测[J].中国水运,2012,12(12):23-25,27.
[4]杨金花,杨艺.基于灰色模型的上海港集装箱吞吐量预测[J].上海海事大学学报,2014,35(2):28-32.
[5]陈昌源,戴冉,杨婷婷,等.基于改进GM(1,1)模型的上海港集装箱吞吐量预测[J].船海工程,2016,45(4):153-156.
[6]崔巍,叶佳.基于三次指数平滑的珠江内河集装箱吞吐量预测[J].珠江水运,2011(12):112-114.
[7]关克平,齐梦雅.基于指数平滑法的宁波舟山港港口吞吐量预测研究[J].中国水运,2013,13(12):28-29.
[8]范莹莹,余思勤.基于NARX神经网络的港口集装箱吞吐量预测[J].上海海事大学学报,2015,36(4):1-5. DOI:10. 13340/j. jsmu.2015. 04. 001.
[9]刘长俭,张庆年.基于时间序列BP神经网络的集装箱吞吐量动态预测[J].水运工程,2007(1):4-11.
[10]王再明,王宏波.灰色系统理论在港口吞吐量预测中的应用[J].武汉理工大学学报(交通科学与工程版),2005,29(3):456-459.
[11]陈秀瑛,古浩.灰色线性回归模型在港口吞吐量预测中的应用[J].水运工程,2010(5):89-92.
[12]徐国祥.统计预测和决策[M].上海:上海财经大学出版社,2006:202-216.
[13]王璐,王沁. SPSS统计分析基础、应用与实战精粹[M].北京:化学工业出版社,2012:230-256.
[14]陈羽. 2015年我国港口集装箱发展现状及趋势[J].中国港口,2016(4):48-53.