[1]刘海宏,刘 敏,朱岸青.基于改进Transformer时序算法的区域经济预测[J].南京师大学报(自然科学版),2024,(04):118-125.[doi:10.3969/j.issn.1001-4616.2024.04.013]
　Liu Haihong,Liu Min,Zhu Anqing.Regional Economic Forecasting Based on Improved Transformer Sequence Algorithm[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(04):118-125.[doi:10.3969/j.issn.1001-4616.2024.04.013]
点击复制

基于改进Transformer时序算法的区域经济预测()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2024年04期
页码:
118-125
栏目:
计算机科学与技术
出版日期:
2024-12-15

文章信息/Info

Title:
Regional Economic Forecasting Based on Improved Transformer Sequence Algorithm
文章编号:
1001-4616(2024)04-0118-08
作者:
刘海宏1; 刘 敏2; 朱岸青3
(1.广州南洋理工职业学院经济管理学院,广东 广州 510900)
(2.西南石油大学计算机与软件学院,四川 南充 637001)
(3.暨南大学管理学院,广东 广州 510000)
Author(s):
Liu Haihong1; Liu Min2; Zhu Anqing3
(1.School of Economics and Management,Guangzhou Nanyang Polytechnic College,Guangzhou 510900,China)
(2.School of Computer and Software,Southwest Petroleum University,Nanchong 637001,China)
(3.School of Management,Jinan University,Guangzhou 510000,China)
关键词:
区域经济预测; Transformer; Copula函数; 主成分分析; 多头注意力
Keywords:
regional economic forecasting; Transformer; Copula function; principal component analysis; multi-head attention
分类号:
TP391
DOI:
10.3969/j.issn.1001-4616.2024.04.013
文献标志码:
A
摘要:
现有的区域经济预测模型指标变量存在冗余,且忽略了行业、区域等静态变量对预测结果的影响,导致预测效率不高. 针对上述问题,提出了基于改进Transformer时序算法的区域经济预测模型. 首先利用Copula函数对传统Transformer模型进行优化(Coformer); 其次选取区域经济的影响指标,对其进行主成分分析,去除冗余信息; 然后将降维后的指标变量和静态变量作为Coformer的输入,对变量进行编码,并通过多头注意力机制增强重要信息,最后用解码器对编码的变量解码,利用Softmax输出区域历年生产总值序列的预测结果. 实验结果表明,所提模型的预测准确率为0.908,比另外三种模型分别提高了15.9%、12.3%和6.7%,表现出了优异的预测性能.
Abstract:
The existing regional economic forecasting model indicators are redundant and ignore the impact of static variables such as industry and region on the forecast results,leading to low forecasting efficiency. In response to the above issues,a regional economic forecasting model based on an improved Transformer time series algorithm is suggested. Firstly,the traditional Transformer model is optimized using a Copula function(Coformer); secondly,the impact indicators of the regional economy are selected,and principal component analysis is performed on them to remove redundant information; then,the reduced-dimensional indicator variables and static variables are used as the input of the Coformer,and the variables are encoded. Finally,the decoder decodes the encoded variables and uses Softmax to output the prediction results of the regional gross domestic product series over the years. The experimental outcome indicates that the designed model has an accuracy of 0.908,which is 15.9%,12.3% and 6.7% higher than the other three models,respectively,demonstrating excellent predictive performance.

参考文献/References:

[1]邹子建. 基于BP神经网络的衡水市经济预测研究[D]. 咸阳:西北农林科技大学,2010.
[2]LEHMANN R,WOHLRABE K. Boosting and regional economic forecasting:the case of Germany[J]. Letters in spatial and resource sciences,2017,10:161-175.
[3]CAPELLO R. A forecasting territorial model of regional growth:the MASST model[J]. The annals of regional science,2007,41:753-787.
[4]LI M,SUN H,AGYEMAN F O,et al. Analysis of potential factors influencing China's regional sustainable economic growth[J]. Applied sciences,2021,11(22):10832.
[5]YOUSSEF J,ISHKER N,FAKHREDDINE N. Economic forecast of the wealthiest gulf countries using ARIMA model[J]. Journal of applied economic sciences,2021,16(2):228-237.
[6]ZHOU W,CHENG Y,DING S,et al. A grey seasonal least square support vector regression model for time series forecasting[J]. ISA transactions,2021,114:82-98.
[7]YU N,XU W,YU K L. Research on regional logistics demand forecast based on improved support vector machine:a case study of Qingdao city under the New Free Trade Zone Strategy[J]. IEEE access,2020,8:9551-9564.
[8]ALAMINOS D,BECERRA-VICARIO R,FERNáNDEZ-GáMEZ M á,et al. Currency crises prediction using deep neural decision trees[J]. Applied sciences,2019,9(23):5227.
[9]WANG J,LI Y,SONG J. Research on regional economic development difference forecast based on BP neural network[J]. Forest chemicals review,2022:952-963.
[10]高振斌,秦轩. 基于PLS-GA-SVR的区域经济预测模型及实证[J]. 统计与决策,2022,38(18):54-57.
[11]ZHANG K,THÉ J,XIE G,et al. Multi-step ahead forecasting of regional air quality using spatial-temporal deep neural networks:a case study of Huaihai Economic Zone[J]. Journal of cleaner production,2020,277:123231.
[12]WAN Y,TAO H,MA L. Forecasting Zhejiang Province's GDP using a CNN-LSTM model[J]. Frontiers in business,economics and management,2024,13(3):233-235.
[13]LABORDA J,RUANO S,ZAMANILLO I. Multi-country and multi-horizon GDP forecasting using temporal fusion transformers[J]. Mathematics,2023,11(12):2625.
[14]HAN Y,TIAN Y,YU L,et al. Economic system forecasting based on temporal fusion transformers:multi-dimensional evaluation and cross-model comparative analysis[J]. Neurocomputing,2023,552:126500.
[15]周湘贞,李帅,隋栋.基于深度学习和注意力机制的微博情感分析[J]. 南京师大学报(自然科学版),2023,46(2):115-121.
[16]宋继勐,周春雷,沈子奇,等. 基于TCN-GRU的Handle标识解析系统负载均衡算法[J]. 福建师范大学学报(自然科学版),2024,40(2):64-73.
[17]李庆涛,林培光,王基厚,等. 基于板块效应的深度学习股价走势预测方法[J]. 南京师范大学学报(工程技术版),2022,22(1):30-38.
[18]项晓宇,朱敏捷,周灵刚,等. 基于机器学习的短期规上行业工业增加值预测[J]. 南京师大学报(自然科学版),2023,46(2):99-106.

备注/Memo

备注/Memo:
收稿日期:2024-07-30.
基金项目:广东省哲学社会科学规划项目(GD22XYJ28)、广东省教育厅项目(2021GXJK595、2021TSZK021).
通讯作者:刘海宏,博士,副教授,研究方向:人工智能与大数据,经济管理. E-mail:8928114@qq.com
更新日期/Last Update: 2024-12-15