•  
  •  
 

Scientific Information Research

Keywords

machine learning; GDP forecast; neural network; review; comparative analysis

Abstract

[Purpose/significance]With the continuous breakthrough in the research of machine learning algo-rithm,its application in the field of GDP prediction is becoming more and more extensive.Systematically combing the relevant topics in this field will contribute to the in-depth development of academic research. [Method/process]Using the method of literature analysis,this paper summarizes the published academic achievements,and combs the research progress and context of machine learning in the field of GDP prediction.[Result/conclusion]The short-term prediction function based on grey prediction model,factor model,traditional time series and dynamic factor model is gradually extended to the long-term prediction function with neural network as the core while support vector machine and Bayesian algorithm as the supplement.At the same time,various researches improve the prediction accuracy by comparing the models and using different models to make combined prediction.This also promotes the modeling idea to change from linear to nonlinear,and from focusing on model parameter optimization to combining with other methods.In addition,the diversity of algorithm improvement and model application,and the multi-dimensional comparison between different models are still the focus and difficulty of this field.Future research can try to achieve more effective combination on the basis of in-depth comparison of various models,and design the potential prediction ability of unused models.

First Page

73

Reference

[1] 王昊,邓三鸿,朱立平,等.大数据环境下政务数据的情报价值及其利用研究:以海关报关商品归类风险规避为例[J].科技情报研究,2020,2(04):74-89.
[2] 陈志高.遗传算法和BP神经网络在GDP预测中的应用[J].计算机与数字工程,2009,37(09):172-175.
[3] 喻胜华,邓娟.基于主成分分析和贝叶斯正则化BP神经网络的GDP预测[J].湖南大学学报(社会科学版),2011,25(06):42-45.
[4] 郭秋艳,何跃.基于DFA方法和BP神经网络的GDP预测模型[J].统计与决策,2014(08):82-84.
[5] 赵军豪,李玉华,霍林,等.融合微博情感分析和深度学习的宏观经济预测方法[J].计算机应用,2018,38(11):3057-3062.
[6] 陈锦皓,郭黎,李润泽,等.基于支持向量机的发电量对GDP的预测[J].湖北民族学院学报(自然科学版),2019,37(01):109-115.
[7] 张学工.关于统计学习理论与支持向量机[J].自动化学报,2000(01):36-46.
[8] 李运蒙,肖健华.基于支持向量机的短期GDP预测模型与应用研究[J].内蒙古大学学报(自然科学版),2004(04):438-441.
[9] 胡艳国,武友新,江恭和.支持向量机在GDP回归预测中的应用研究[J].微计算机信息,2007(33):17-18,9.
[10] PERIKLIS G,THEOPHILOS P,ELVIRA T.Comparison of Simple Sum and Divisia Monetary Aggregates in GDP Forecasting:a Support Vector Machines Approach[J].Economics Bulletin,2013,39(02):1101-1115.
[11] 林琦.基于最小二乘支持向量机的福建省GDP预测研究[J].科学技术与工程,2009,9(22):6856-6858.
[12] ELMIRA E,CAGAY C.Economic Growth Prediction Using Optimized Support Vector Machines [J].Computational Economics,2016,48(07):453-462.
[13] KOUZIOKAS GN.A new W-SVM kernel combining PSO-neural network transformed vector and Bayesian optimized SVM in GDP forecasting [J].Engineering Applications of Artificial Intelligence,2020,92(03):103-106.
[14] 丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(01):2-10.
[15] 奉国和.SVM分类核函数及参数选择比较[J].计算机工程与应用,2011,47(03):123-124,128.
[16] 喻凯西.朴素贝叶斯分类算法的改进及其应用[D].北京:北京林业大学,2016.
[17] MARTIN LC.Machine Learning vs Traditional Forecasting Methods:An Application to South African GDP[J].SA-TIED Working Paper,2019,22(02):45.
[18] 刘国旺,熊健.基于MCMC方法的ARFIMA模型贝叶斯分析及实证研究[J].数理统计与管理,2012,31(03):434-439.
[19] 熊健,尹姗姗.基于贝叶斯估计的中国人均GDP之时序模型[J].数理统计与管理,2016,35(04):623-629.
[20] 张静.基于贝叶斯时序模型的甘肃省人均GDP预测[J].数理统计与管理,2018,37(02):205-210.
[21] 江川,王东波.基于BERT的突发公共卫生重大传染病事件实体知识自动抽取研究[J].科技情报研究,2021,3(02):23-35.
[22] 毛太田,王诗玉.基于AHP-BP神经网络的政府信息资源配置评价研究[J].科技情报研究,2020,2(01):66-73.
[23] 毛健,赵红东,姚婧婧.人工神经网络的发展及应用[J].电子设计工程,2011,19(24):62-65.
[24] GREG T,SARAH H.Forecasting GDP Growth Using Artificia Neura Networks[J].Staff Working Paper,1999,10(01):3.
[25] GREG T.Neural network forecasting of Canadian GDP growth[J].International Journal of Forecasting,2001,17(01):57-69.
[26] 欧邦才.基于BP神经网络的经济预测方法[J].南京工程学院学报(自然科学版),2004(02):11-14.
[27] 余国合,俞良蒂.基于BP神经网络的GDP增长率预测[J].统计与决策,2005(05):14-15.
[28] FARZAN A,EDANTE S,MEHRAN A,et al.Forecasting Economic Data with Neural Networks[J].Computational Economics,2006,28(03):71-88.
[29] 蒋雪,王顶.基于BP神经网络技术的GDP预测方法[J].经济论坛,2010(03):203-204.Â
[30] JAHN M.Artificial neural network regression models:Predicting GDP growth[J].HWWI Research Paper,2018,10(08):185.
[31] JAHN M.Artificial neural network regression models in a panel setting:Predicting economic growth[J].Economic Modelling,2020:148-154.
[32] PRADYOT R J,RITANJALI M,RAJESH K,et al.Impact of COVID-19 on GDP of major economies: Application of the artificial neural network forecaster[J].Economic Analysis and Policy,2021,69(06):324-339.
[33] 李颖,谭广.新冠肺炎疫情对我国季度GDP增速影响估测:基于机器学习回归预测模型[J].中国农业会计,2021(03):39-42.
[34] 王宇,李旭东.基于BP神经网络的我国M2/GDP预测与对策[J].生态经济,2007(09):48-51.
[35] 梁娜,张吉刚.基于改进BP的GDP预测研究[J].计算机与数字工程,2012,40(01):49-50,53.
[36] 刘攀,冯长焕.EGM-BP网络模型在单变量时间序列预测中的应用:以四川省GDP为例[J].廊坊师范学院学报(自然科学版),2017,17(03):8-11.
[37] HALTIWANGER J,JARMIN R S.Measuring the digital economy[J].Understanding the Digital Economy: Data,Tools,and Research,1999,5(01):29-30.
[38] CHUKU C,ANTHONY S,JACOB O.Intelligent forecasting of economic growth for developing economies[J].International Economics,2019,159(01):74-93.
[39] 杨娟丽,徐梅,王福林,等.基于BP神经网络的时间序列预测问题研究[J].数学的实践与认识,2013,43(04):158-164.
[40] 黄丽.BP神经网络算法改进及应用研究[D].重庆:重庆师范大学,2008.
[41] DUŠAN M,DALIBOR P,VLASTIMIR N,et al.Soft computing prediction of economic growth based in science and technology factors[J].Statistical Mechanics and its Applications,2017,465(08):217-220.
[42] BOJANA J,BOJAN L,MILOŠ M,et al.Economic development evaluation based on science and patents[J].Statistical Mechanics and its Applications,2017,481(01):141-145.
[43] SVETLANA SM,MILOS M,IGOR M,et al.Economic growth forecasting by artificial neural network with extreme learning machine based on trade,import and export parameters[J].Computers in Human Behavior,2016,65(02):43-45.
[44] BOJANA K,LIDIJA B,LJILJANA J,et al.Appraisal of artificial neural network for forecasting of economic parameters[J].Statistical Mechanics and its Applications,2017,465(01):515-519.
[45] DUŠAN C,MEYSAM A,IVAN P,et al.A machine learning approach for predicting the relationship between energy resources and economic development[J].Statistical Mechanics and its Applications,2018,30(09):211-214.
[46] LJUBIŠA M,SRĐAN J,TANJA V,et al.Application of artificial neural network with extreme learning machine for economic growth estimation[J].Statistical Mechanics and its Applications,2017,465(01):285-288.
[47] MIRJANA S,SLAĐANA V,ALEKSANDAR MG.Gross domestic product estimation based on electricity utilization by artificial neural network[J].Statistical Mechanics and its Applications,2018,489(01):28-31.
[48] 朱青,周石鹏.基于LSTM模型的国民经济GDP增长预测建模研究[J].经济研究导刊,2021(19):5-9,37.
[49] 肖争艳,刘玲君,赵廷蓉,等.深度学习神经网络能改进GDP的预测能力吗?[J].经济与管理研究,2020,41(07):3-17.
[50] Kurihara Y,Fukushima A.AR Model or Machine Learning for Forecasting GDP and Consumer Price for G7 Countries[J].Applied Economics and Finance,2019,6(03):1-3.
[51] ISLAM R.Predicting Recessions:Forecasting US GDP Growth through Supervised Learning[J].Department of Electrical Engineering,2013,c229.stanford.edu.
[52] SAFI SK.A Comparison of Artificial Neural Network,Time Series Models for Forecasting GDP in Palestine[J].American Journal of Theoretical and Applied,2016,iugspace.iugaza.edu.ps.
[53] 罗森,张孟璇.基于ARIMA和VAR模型的我国季度GDP预测比较[J].现代商业,2019(35):50-52.
[54] RICHARDSON A,MULDER T.Nowcasting New Zealand GDP Using Machine Learning Algorithms[J].CAMA Working Paper,2018,5(03):109-189.
[55] KOHEI M,MOTOTSUGU S.Macroeconomic forecasting using factor models and machine learning:an application to Japan[J].Journal of the Japanese and International Economies,2020,58(05):101-104.
[56] 何强,董志勇.利用互联网大数据预测季度GDP增速的方法研究[J].统计研究,2020(12):91-104.
[57] 李佳,黄之豪,王佳慧.基于独立循环神经网络方法的GDP预测[J].统计与决策,2020(14):24-28.
[58] YOON J.Forecasting of Real GDP Growth Using Machine Learning Models:Gradient Boosting and Random Forest Approach[J].Computational Economics,2021,57(02):247-265.
[59] SOYBILGEN B,YAZGAN E.Nowcasting us gdp using tree-based ensemble models and dynamic factors[J].Computational Economics,2021,57(01):387-417.
[60] DAVID A,BELÉN SM,MANUEL A FG.Quantum Computing and Deep Learning Methods for GDP Growth Forecasting[J].Computational Economics,2022,59(02),803-829.
[61] CHU B,QURESHI S.Comparing Out-of-Sample Performance of Machine Learning Methods to Forecast U.S.GDP Growth[J].Carleton Economics Working Papers,2021,3(04):100-104.
[62] 徐映梅,陈尧.季节ARIMA模型与LSTM神经网络预测的比较[J].统计与决策,2021(02):46-50.
[63] 腾格尔,何跃.基于GMDH组合的中国GDP预测模型研究[J].统计与决策,2010(07):17-19.
[64] 许金炜.基于虚拟变量回归与SARIMA组合模型的GDP预测[J].统计与决策,2016(24):38-41.
[65] 王莎莎,陈安,苏静,等.组合预测模型在中国GDP预测中的应用[J].山东大学学报(理学版),2009,44(02):56-59.
[66] 余后强,李玲.我国人均国内生产总值的预测分析[J].统计与决策,2012(04):103-106.
[67] 陈黎明,傅珊.基于组合预测模型的GDP统计数据质量评估研究[J].统计与决策,2013(08):8-11.
[68] 由向平,孙德山,林丹凤.组合模型在我国GDP预测中的应用[J].廊坊师范学院学报(自然科学版),2010,10(02):87-89.
[69] 张劲帆,刚健华,钱宗鑫,等.基于混频向量自回归模型的宏观经济预测[J].金融研究,2018(07):34-48.
[70] 张鹏.改进的ARIMA-GM-SVR组合预测模型及应用[J].统计与决策,2019(13):82-84.
[71] WOCHNER,DANIEL.Dynamic Factor Trees and Forests-A Theory-led Machine Learning Framework for Non-Linear and State-Dependent Short-Term U.S.GDP Growth Predictions[J/OL].KOF Working Papers,2010:https://doi.org/10.3929/ethz-b-000399304.
[72] 魏仕强,何跃,蒋薇.基于ARMA-ARCH的GDP组合预测[J].统计与决策,2007(10):21-22.
[73] 熊志斌.基于ARIMA与神经网络集成的GDP时间序列预测研究[J].数理统计与管理,2011,30(02):306-314.
[74] 莫东序.ARIMA与BP神经网络混合模型在广西GDP预测中的应用[J].广西财经学院学报,2011,24(06):31-34.
[75] 王鑫,肖枝洪.基于干预模型与BP神经网络集成的GDP预测[J].统计与决策,2012(20):141-144.
[76] 罗志丹,刘英.中国季度GDP预测模型的比较[J].统计与决策,2020(05):33-37.
[77] 刘全,刘汀.基于ARIMA的多元时间序列神经网络预测模型研究[J].统计与决策,2009(11):23-25.
[78] MIRBAGHERI M.Fuzzy-logic and Neural network Fuzzy forecasting of Iran GDP growth[J].African Journal of Business Management,2010,4(06):925-929.
[79] LUIGI L,MASSIMO R,ARMANDO R.A neural network ensemble approach for GDP forecasting[J].Journal of Economic Dynamics and Control,2022,134(15):104-278.
[80] 宣平,刘建宁,李国成.基于灰色BP网络的GDP总量组合预测模型应用研究[J].黄山学院学报,2009,11(03):44-47.
[81] 何刚,吴文青,夏杰.基于Simpson公式的灰色神经网络在GDP预测中的应用[J].统计与决策,2020(02):43-47.
[82] 龙会典,严广乐.基于SARIMA、GM(1,1)和BP神经网络集成模型的GDP时间序列预测研究[J].数理统计与管理,2013,32(05):814-822.
[83] 谢成兴,王丰效.基于ARIMA-DGM-BP组合模型的喀什地区GDP预测[J].数学的实践与认识,2020,50(15):43-48.
[84] FORNARO P,LUOMARANTA H.Nowcasting Finnish real economic activity:a machine learning approach[J].Empirical Economics,2020,58(01):55-71.
[85] 吴睿辉,周湘贞.基于大数据驱动的地方经济短期预测研究[J].辽宁科技大学学报,2020,43(04):304-308.
[86] 何清,李宁,罗文娟,等.大数据下的机器学习算法综述[J].模式识别与人工智能,2014,27(04):327-336.
[87] 张和平,陈齐海.基于等维新息递补GM(1,1)幂模型的GDP预测[J].统计与决策,2017(21):68-70.
[88] 何黎,何跃.结合PMI的中国GDP预测模型[J].统计与决策,2012(01):84-86.
[89] 郭晓峰.基于ARIMA模型的中国CPI走势预测分析[J].统计与决策,2012(11):29-32.
[90] SCHUMACHER C,BREITUNG J.Real-time forecasting of German GDP based on a large factor model with monthly and quarterly data[J].International Journal of Forecasting,2008,24(03):386-398.
[91] JAHN M.Artificial neural network regression models in a panel setting:Predicting economic growth[J]. Economic Modelling,2020(91):148-154.
[92] URASAWA S.Real-time GDP forecasting for Japan:A dynamic factor model approach[J].Journal of the Japanese and International Economies,2014(34):116-134.
[93] ZHANG Y,CINDY L Y,LI H.Nowcasting GDP Using Dynamic Factor Model with Unknown Number of Factors and Stochastic Volatility:A Bayesian Approach[J/OL].Econometrics and Statistics,2021,https://doi.org/10.1016/j.ecosta.2021.08.009.
[94] 张润,王永滨.机器学习及其算法和发展研究[J].中国传媒大学学报(自然科学版),2016(02):10-18.
[95] 王英伟,马树才.基于ARIMA和LSTM混合模型的时间序列预测[J].计算机应用与软件,2021,38(02):291-298.
[96] 高金敏,郭佩佩.基于自回归XGBoost时序模型的GDP预测实证[J].数学的实践与认识,2021,51(07):9-16.
[97] BAŃBURA M,RÜNSTLER G.A look into the factor model black box:publication lags and the role of hard and soft data in forecasting GDP[J].International Journal of Forecasting,2011,27(02):333-346.

Share

COinS