随着我国对外贸易的发展以及经济结构的改革，在宏观调控中需要把握国际收支的格局演变，但是在多变的国际环境和形势下，中国的经常账户面临着不确定性.因此本文基于国际收支平衡表中的经常账户的借贷方数据，采用EEMD-AWNN集成学习方法对经常账户进行预测.传统的计量模型所估计的结果虽然有较好的经济解释，但很难适应国内与国际经济结构的快速变化.单变量机器学习算法虽然能适应国内与国际经济结构的变化，但其对外生的经济变量不够敏感.基于此，本文基于TEI@I方法论的思想，首先使用经验模态分解（EEMD）将需要预测的变量进行分解，再根据经济意义加入需要的外生变量，利用所提出的自适应小波神经网络（AWNN）对其进行单一预测与集成.预测结果显示，EEMD-AWNN算法的预测精度要明显高于计量经济模型.最终预测结果显示未来两年经常账户各主要项目借方贷方将继续增长，但由于货物借方和旅行借方未来的增速高于货物贷方和旅行贷方，货物贸易顺差将收窄，同时旅行贸易逆差加大，两者共同导致经常账户顺差将减小.
Abstract
With the development of China's foreign trade and economic structure reform, it is necessary to explore the evolution of the balance of payments for the macroeconomic regulation, but China is faced with uncertainty of the current account due to the changeable international environment. Based on this background, The EEMD-AWNN model is proposed to predict the current account, including debit and credit. Traditional econometric model can give economic explanation, but it is difficult to adapt to the rapid change of domestic and international economic structure. In addition, the single-variable machine learning algorithm can overcome this problem, but it is not sensitive enough to the external economic variables. Therefore, this paper learns from TEI@I and proposes EEMD-AWNN model to predict the current account. In EEMD-AWNN, the empirical mode decomposition (EEMD) is first used to decompose the variables, and then required exogenous variables are added according to economic significance. Finally, the synthesized adaptive wavelet neural network (AWNN) is used to predict the current account, which obtains higher accuracy and better forecasting performance than econometric models. Based on the proposed model, the results showed that both debit and credit of the current account will grow. However, the debit growth rates of trade in goods and service trade will be higher than their credit growth rate. What's more, the surplus of commodity trade will narrow and travel trade deficit will increase. Therefore, China's current account will continue to run a surplus but the surplus will narrow in next two years.
关键词
预测 /
经常账户 /
集成学习 /
自适应小波神经网络 /
经验模态分解
{{custom_keyword}} /
Key words
forecasting /
current account /
ensemble learning /
adaptive wavelet neural network /
empirical mode decomposition
{{custom_keyword}} /
中图分类号：
F830.9
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 田开兰,杨翠红.中欧光伏贸易争端对双方经济损益的影响分析[J].系统工程理论与实践, 2016, 36(7):1652-1660.Tian K L, Yang C H. Analysis of the impact of Sino-European PV trade disputes on the economic profit and loss of both sides[J]. Systems Engineering-Theory & Practice, 2016, 36(7):1652-1660.
[2] 段文奇,刘宝全,季建华.国际贸易网络拓扑结构的演化[J].系统工程理论与实践, 2008, 28(10):71-81.Duan W Q, Liu B Q, Ji J H. The evolution of topological structure of international trade network[J]. Systems Engineering-Theory & Practice, 2008, 28(10):71-81.
[3] 刘伟,张贵先. FDI与中国经常项目的实证分析[J].财经问题研究, 2010(2):68-73.Liu W, Zhang G X. Empirical analysis of FDI and China's current account[J]. Research on Financial Issues, 2010(2):68-73.
[4] 李新.关于我国经常项目差额变动的研究[D].成都:西南财经大学, 2014.Li X. Research on the change of China's current account balance[D]. Chengdu:Southwest University of Finance and Economics, 2014.
[5] 杨文兰.中国贸易结构失衡问题研究——基于贸易收支视角[J].经济论坛, 2011(3):32-36.Yang W L. A study on the imbalance of China's trade structure-from the perspective of trade balance[J]. Economic Forum, 2011(3):32-36.
[6] 王玉荣. ARIMA模型在我国出口贸易预测中的应用[J].决策参考, 2004(4):33-34.Wang Y R. The application of ARIMA model in the prediction of China's export trade[J]. Decision Reference, 2004(4):33-34.
[7] 张嘉为,陈曦,汪寿阳.新的空问权重矩阵及其在中国省域对外贸易中的应用[J].系统工程理论与实践, 2009, 29(11):84-91.Zhang J W, Chen X, Wang S Y. A new spatial weight matrix and its application in China's provincial foreign trade[J]. Systems Engineering-Theory & Practice, 2009, 29(11):84-91.
[8] 陈久超. GMDH网络在进出口贸易预测中的应用[J].信息技术, 2014(8):199-201.Chen J C. The application of GMDH network in the prediction of import and export trade[J]. Information Technology, 2014(8):199-201.
[9] 陈蔚.基于线性ARIMA与非线性BP神经网络组合模型的进出口贸易预测[J].统计与决策, 2015(22):47-49.Chen W. Forecast of import and export trade based on the combination model of linear ARIMA and nonlinear BP neural network[J]. Statistics and Decision Making, 2015(22):47-49.
[10] 白霜.基于PSO优化混合RVM模型的进出口贸易预测算法[J].计算机与现代化, 2014(8):110-118.Bai S. Prediction algorithm of import and export trade based on PSO optimized hybrid RVM model[J]. Computer and Modernization, 2014(8):110-118.
[11] 汪寿阳,余乐安,黎建强. TEI@I方法论及其在外汇汇率预测中的应用[J].管理学报, 2007, 4(1):21-27.Wang S Y, Yu L A, Lai K K. TEI@I methodology and its application in foreign exchange rate prediction[J]. Journal of Management, 2007, 4(1):21-27.
[12] 王晓丹,尚维,汪寿阳.互联网新闻媒体报道对我国股市的影响分析[J].系统工程理论与实践, 2019, 39(12):3038-3047.Wang X D, Shang W, Wang S Y. The effects of online news on the Chinese stock market[J]. Systems Engineering-Theory & Practice, 2019, 39(12):3038-3047. ewpage
[13] 李兵,林安琪,郭冬梅.经济政策不确定性对进口产品的异质性影响——基于中文报纸大数据文本的实证分析[J].系统工程理论与实践, 2020, 40(6):1578-1595.Li B, Lin A Q, Guo D M. Product heterogeneous effects of economic policy uncertainty on imports:Big data context analysis based on Chinese newspapers[J]. Systems Engineering-Theory & Practice, 2020, 40(6):1578-1595.
[14] 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.
[15] Wu Z, Huang N. Ensemble empirical mode decomposition:A noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1:1-41.
[16] Huang N, Shen Z, Long S. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical, Physical and Engineering Sciences, 1998, 454:903-995.
[17] Billings S A, Wei H L. A new class of wavelet networks for nonlinear system identification[J]. IEEE Transactions on Neural Networks, 2005, 16(4):862-874.
[18] Zhang Q, Benveniste A. Wavelet networks[J]. IEEE Transactions on Neural Networks, 1992, 3(6):889-898.
[19] Iyengar S S, Phoha V V. Foundations of wavelet networks and applications[M]. CRC Press, 2002.
[20] Zhang Q. Using wavelet network in nonparametric estimation[J]. IEEE Transactions on Neural networks, 1997, 8(2):227-236.
[21] Wang S Y. TEI@I:A new methodology for studying complex systems[C]//Workshop on Complexity Science, Tsukuba, April 22-23, 2004.
[22] Wang S Y, Yu L A. TEI@I:A new methodology for studying volatility of international oil price[C]//Conference of International Research Team of AMSS on Complexity Science, Beijing, June 17-19, 2004.
[23] Wang S Y, Yu L A, Lai K K. Crude oil price forecasting with TEI@I methodology[J]. Journal of Systems Sciences and Complexity, 2005, 18(2):145-166.
[24] Yu L A, Wang S Y, Lai K K. Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm[J]. Energy Economics, 2008, 30(5):2623-2635.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金（71988101）
{{custom_fund}}
PDF(1026 KB)
