基于二次分解和模型选择策略的港口集装箱吞吐量组合预测

管理评论 ›› 2024, Vol. 36 ›› Issue (8): 52-64.

• 经济与金融管理 • 上一篇

基于二次分解和模型选择策略的港口集装箱吞吐量组合预测

梁小珍¹, 赵欣¹, 杨明歌¹, 吴俊峰², 邓天虎³, 田歆^4,5

1. 上海大学管理学院, 上海 200444;
2. 上海文景信息科技有限公司, 上海 200126;
3. 清华大学工业工程系, 北京 100084;
4. 中国科学院大学经济与管理学院, 北京 100190;
5. 中国科学院虚拟经济与数据科学研究中心, 北京 100190

收稿日期:2021-11-26 发布日期:2024-09-03
作者简介:梁小珍，上海大学管理学院副教授，硕士生导师，博士;赵欣，上海大学管理学院硕士研究生;杨明歌，上海大学管理学院副教授，硕士生导师，博士;吴俊峰，上海文景信息科技有限公司董事长、总经理;邓天虎，清华大学工业工程系长聘副教授，博士生导师，博士;田歆(通讯作者)，中国科学院大学经济与管理学院教授、中国科学院虚拟经济与数据科学研究中心研究员，博士生导师，博士。
基金资助:
国家自然科学基金项目(71701122；11801352；72172145；71932002)；北京市自然科学基金项目(9212020)；中央高校基本科研业务费专项资金。

A Combination Forecast Method of Port Container Throughput Based on Secondary Decomposition and Model Selection Strategy

Liang Xiaozhen¹, Zhao Xin¹, Yang Mingge¹, Wu Junfeng², Deng Tianhu³, Tian Xin^4,5

1. School of Management, Shanghai University, Shanghai 200444;
2. Shanghai WinJoin Information Technology Co., Ltd., Shanghai 200126;
3. Department of Industrial Engineering, Tsinghua University, Beijing 100084;
4. School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190;
5. Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing 100190

Received:2021-11-26 Published:2024-09-03

摘要/Abstract

摘要： 准确预测港口集装箱吞吐量对于政府部门规划港口建设,港口和航运企业合理调配资源具有重要意义。已往研究往往采用单一分解方法来处理序列中的复杂特征,存在数据特征提取不完全以及预测模型选择比较盲目的问题,极大地影响了组合模型的预测效果。为此,本文引入二次分解和基于数据特征的模型选择策略,通过建立组合预测框架对港口集装箱吞吐量进行预测。首先,根据原始序列的整体特征选择一种分解方法对其进行初步分解,得到若干分量。然后,分析各分量的平稳性、季节性及复杂性等数据特征,据此选择合适的计量经济学模型进行预测或采用完全自适应噪声集合经验模态分解(CEEMDAN)方法对分量进行二次分解。接着,引入长程相关性特征,根据二次分解后子序列的平稳性、复杂性、长程相关性等再选择合适的预测模型。最后,将所有分量的预测结果集成从而得到最终的预测值。以月度预测为例,本文选取上海港和天津港集装箱吞吐量数据作为样本开展实证研究。实证结果表明,本文所提出的组合预测框架与基准模型相比具有更高的预测精度,是一种比较有前景的港口集装箱吞吐量预测工具,可以为相关政府部门、港口及航运企业提供决策参考。

关键词: 集装箱吞吐量预测, 二次分解, 数据特征分析, 模型选择, 组合预测

Abstract: Accurate prediction of port container throughput is of great significance to government planning of port construction and reasonable allocation of resources by ports and shipping enterprises. Previous studies often use a single decomposition method to deal with the complex features in the container throughput series, which results in incomplete data feature extraction and blind selection of prediction models, and greatly affects the prediction effect of the combined model. Therefore, this paper introduces the strategies of secondary decomposition and model selection based on data characteristics analysis to predict the port container throughput by establishing a combination forecast framework. Firstly, according to the overall characteristics of the original series, a decomposition method is selected to decompose it preliminarily, and several components are obtained. Then, the data characteristics of each component, such as stationarity, seasonality and complexity, are analyzed, and an appropriate econometric model is selected for prediction or the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method is used to decompose the component. Next, the characteristic of long-range correlation is introduced, and the appropriate model for prediction is selected according to the stationarity, complexity, and long-range correlation of the sub-sequences after the secondary decomposition. Finally, the predicted values of all components are integrated to obtain the final prediction results. Taking monthly forecast as an example, the empirical study uses the container throughput data of Shanghai Port and Tianjin Port as samples. The empirical results show that the combination forecast framework proposed in this paper has higher prediction accuracy than the benchmark models, and is a promising tool for port container throughput forecasting, which can provide decision-making reference for relevant government departments, ports, and shipping enterprises.

Key words: forecast of container throughput, secondary decomposition, data characteristics analysis, model selection, combination forecast

梁小珍, 赵欣, 杨明歌, 吴俊峰, 邓天虎, 田歆. 基于二次分解和模型选择策略的港口集装箱吞吐量组合预测[J]. 管理评论, 2024, 36(8): 52-64.

Liang Xiaozhen, Zhao Xin, Yang Mingge, Wu Junfeng, Deng Tianhu, Tian Xin. A Combination Forecast Method of Port Container Throughput Based on Secondary Decomposition and Model Selection Strategy[J]. Management Review, 2024, 36(8): 52-64.

参考文献

[1] 吴佳璋,徐艺文. 中国港口:持续复苏强劲增长[J]. 中国远洋海运, 2021,(7):50-54 Wu J. Z., Xu Y. W. China's Ports:Sustained Recovery and Strong Growth[J]. Maritime China, 2021,(7):50-54
[2] 鲁渤,杨显飞,汪寿阳. 基于情境变动的港口吞吐量预测模型[J]. 管理评论, 2018,30(1):195-201 Lu B., Yang X. F., Wang S. Y. Port Throughput Forecasting Model Based on Context Change[J]. Management Review, 2018,30(1):195-201
[3] Erdem E., Shi J. ARMA Based Approaches for Forecasting the Tuple of Wind Speed and Direction[J]. Applied Energy, 2011,88(4):1405-1414
[4] Dantas T. M., Oliveira F. L. C., Repolho H. M. V. Air Transportation Demand Forecast through Bagging Holt-Winters Methods[J]. Journal of Air Transport Management, 2017,59(1):113-123
[5] 王书平,朱艳云. 基于多尺度分析的小麦价格预测研究[J]. 中国管理科学, 2016,24(5):85-91 Wang S. P, Zhu Y. Y. Forecasting of Wheatprice Based on Multi-scale Analysis[J]. Chinese Journal of Management Science, 2016,24(5):85-91
[6] Singhal D., Swarup K. Electricity Price Forecasting Using Artificial Neural Networks[J]. Electrical Power and Energy Systems, 2011,33(1):550-555
[7] 肖智,李玲玲. PSO-SVM在高速公路交通量预测中的应用[J]. 管理评论, 2011,23(12):32-37 Xiao Z., Li L. L. Forecast of Highway Traffic Volume Using PSO-SVM[J]. Management Review, 2011,23(12):32-37
[8] Cao Q., Ewing B., Thompson M. Forecasting Wind Speed with Recurrent Neural Networks[J]. European Journal of Operational Research, 2012,221(1):148-154
[9] Shen W., Guo X., Wu C., et al. Forecasting Stock Indices Using Radial Basis Function Neural Networks Optimized by Artificial Fish Swarm Algorithm[J]. Knowledge-Based Systems, 2011,24(1):378-385
[10] 田歆,曹志刚,骆佳伟,等. 基于TEI@I方法论的香港集装箱吞吐量预测方法[J]. 运筹与管理, 2009,18(4):82-89 Tian X., Cao Z. G., Luo J. W., et al. Forecasting the Container Throughput of Hong Kong through TEI@I[J]. Operations Research and Management Science, 2009,18(4):82-89
[11] 周桦,卢志源,郑敏. 基于TEI@I方法的中国保险业保费收入预测[J]. 管理评论, 2020,32(7):166-179 Zhou H., Lu Z. Y., Zheng M. Forecasting Premium Income of China's Insurance Industry Based on TEI@I Methodology[J]. Management Review, 2020,32(7):166-179
[12] 孙少龙,魏云捷,汪寿阳. 基于分解-聚类-集成学习的汇率预测方法[J]. 系统工程理论与实践, 2022,42(3):664-677 Sun S. L., Wei Y. J., Wang S. Y. Exchange Rates Forecasting with Decomposition-Clustering-Ensemble Learning Approach[J]. Systems Engineering-Theory & Practice, 2022,42(3):664-677
[13] Du P., Wang J., Yang W., et al. Container Throughput Forecasting Using a Novel Hybrid Learning Method with Error Correction Strategy[J]. Knowledge-Based Systems, 2019,182(15):104853
[14] 张大斌,蔡超敏,凌立文,等. 基于CEEMD与GA-SVR的猪肉价格集成预测模型[J]. 系统科学与数学, 2020,40(6):1061-1073 Zhang D. B., Cai C. M., Ling L. W., et al. Pork Price Ensemble Prediction Model Based on CEEMD and GA-SVR[J]. Journal of Systems Science and Mathematical Sciences, 2020,40(6):1061-1073
[15] 汤霞,匡海波,郭媛媛,等. 基于VMD的中国出口集装箱运价指数分析与组合预测[J]. 系统工程理论与实践, 2021,41(1):176-187 Tang X., Kuang H. B., Guo Y. Y., et al. Analysis and Combined Forecasting of China Containerized Freight Index Based on VMD[J]. Systems Engineering-Theory & Practice, 2021,41(1):176-187
[16] 梁小珍,郭战坤,张倩文,等. 基于奇异谱分析的航空客运需求分析与分解集成预测模型[J]. 系统工程理论与实践, 2020,40(7):1844-1855 Liang X. Z., Guo Z. K., Zhang Q. W., et al. An Analysis and Decomposition Ensemble Prediction Model for Air Passenger Demand Based on Singular Spectrum Analysis[J]. Systems Engineering-Theory & Practice, 2020,40(7):1844-1855
[17] Tang L., Yu L., He K. A Novel Data-characteristic-driven Modeling Methodology for Nuclear Energy Consumption Forecasting[J]. Applied Energy, 2014,128(1):1-14
[18] Cleveland R. B., Cleveland W. S., McRae J. E., et al. STL:A Seasonal-trend Decomposition Procedure Based on Loess[J]. Journal of Official Statistics, 1990,6(1):3-73
[19] Zhang W., Qu Z., Zhang K., et al. A Combined Model Based on CEEMDAN and Modified Flower Pollination Algorithm for Wind Speed Forecasting[J]. Energy Conversion and Management, 2017,136(1):439-451
[20] Dickey D. A., Fuller W. A. Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root[J]. Econometrica, 1981, 49(4):1057-1072
[21] Phillips P. C. B. Time Series Regression with a Unit Root[J]. Econometrica, 1987,55(2):277-301
[22] Hart T., Coulson T., Trathan P. N. Time Series Analysis of Biologging Data:Autocorrelation Reveals Periodicity of Diving Behaviour in Macaroni Penguins[J]. Animal Behaviour, 2010,79(4):845-855
[23] Shi K., Liu C., Ai N., et al. Using Three Methods to Investigate Time-scaling Properties in Air Pollution Indexes Time Series[J]. Nonlinear Analysis:Real World Applications, 2008,9(2):693-707
[24] Wang J., Li Y. Multi-step Ahead Wind Speed Prediction Based on Optimal Feature Extraction, Long Short Term Memory Neural Network and Error Correction Strategy[J]. Applied Energy, 2018,230(1):429-443
[25] Yu L., Wang Z., Tang L. A Decomposition-ensemble Model with Data-characteristic-driven Reconstruction for Crude Oil Price Forecasting[J]. Applied Energy, 2015,156(1):251-267
[26] Peng C. K., Buldyrev S. V., Havlin S., et al. Mosaic Organization of DNA Nucleotides[J]. Physical Review E Statistical Physics Plasmas Fluids & Related Interdisciplinary Topics, 1994,49(2):1685
[27] Wang J., Yan J., Li C., et al. Deep Heterogeneous GRU Model for Predictive Analytics in Smart Manufacturing:Application to Tool Wear Prediction[J]. Computers in Industry, 2019,111(1):1-14
[28] Tian X., Liu L., Lai K., et al. Analysis and Forecasting of Port Logistics Using TEI@I methodology[J]. Transportation Planning and Technology, 2013,36(8):685-702
[29] 鲁渤,邢戬,王乾,等. 港口竞争力与腹地经济协同机制面板数据分析[J]. 系统工程理论与实践, 2019,39(4):1079-1090 Lu B., Xing J., Wang Q., et al. Analysis of Cooperation Mechanism between Port Competitiveness and Hinterland by Panel Data[J]. Systems Engineering-Theory & Practice, 2019,39(4):1079-1090
[30] Diebold F. X., Mariano R. S. Comparing Predictive Accuracy[J]. Journal of Business & Economic Statistics, 1995,13(3):253-263
[31] 赵奉军,王先柱. 中国土地交易价格季节性的实证检验[J]. 中国土地科学, 2012,26(6):73-78 Zhao F. J., Wang X. Z. An Empirical Test on the Seasonality in China's Land Market[J]. China Land Sciences, 2012,26(6):73-78

基于二次分解和模型选择策略的港口集装箱吞吐量组合预测

A Combination Forecast Method of Port Container Throughput Based on Secondary Decomposition and Model Selection Strategy

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价