主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2021, Vol. 29 ›› Issue (11): 68-77.doi: 10.16381/j.cnki.issn1003-207x.2019.0765

• 论文 • 上一篇    

基于EEMD-LSTM的农产品价格短期预测模型研究

方雪清, 吴春胤, 俞守华, 张大斌, 欧阳庆   

  1. 华南农业大学数学与信息学院,广东 广州510642
  • 收稿日期:2019-05-28 修回日期:2019-12-04 发布日期:2021-11-22
  • 通讯作者: 吴春胤(1972—),男(汉族),浙江人,华南农业大学数学与信息学院,博士,副教授,研究方向:人工智能、经济预测, Email:wuchunyin@scau.edu.cn. E-mail:wuchunyin@scau.edu.cn
  • 基金资助:
    国家社会科学基金资助项目(19BGL256);教育部人文社会科学研究规划项目(16YJA630073)

Research on Short-Term Forecast Model of Agricultural Product Price Based on EEMD-LSTM

FANG Xue-qing, WU Chun-yin, YU Shou-hua, ZHANG Da-bin, OU Yang-qing   

  1. College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
  • Received:2019-05-28 Revised:2019-12-04 Published:2021-11-22
  • Contact: 吴春胤 E-mail:wuchunyin@scau.edu.cn

摘要: 本文将集成经验模态分解(EEMD)方法与长短期记忆网络(LSTM)相结合,构建了一个端到端的农产品价格短期预测模型。首先,对原始价格信号进行EEMD分解,得到若干IMF子序列和一个残差序列;然后,运用Fine-to-coarse高低频重构方法对IMF子序列进行高频—低频重构;最后将原始价格序列、高频项、低频项和残差趋势项作为特征,输入到LSTM网络进行训练得到预测模型。本文以广州市江南农副产品市场的富士苹果日价格为例进行实证分析,结果表明,本文提出的EEMD-LSTM模型在农产品价格短期预测问题上具有一定的性能优势。

关键词: 农产品;短期价格预测;集成经验模态分解;长短期记忆网络

Abstract: Agricultural produces price forecasting is one of the main research issues in the field of agricultural economy, and it is of great interest to many researchers and institutions.A novel method is proposed in this paper for agricultural produces price forecasting based on Ensemble Empirical Mode Decomposition (EEMD) method and Long Short-Term Memory (LSTM) network. First, the original price series is decomposed by EEMD to several IMF subsequences and one residual sequence. Then, the fine-to-coarse method is used to reconstruct the IMF subsequences into high frequency item and low frequency item. Finally, the original price series, high frequency item, low-frequency item and residual sequence are taken as input features to train the LSTM network, so as to construct an EEMD-LSTM combined forecasting model.

Key words: agricultural produces; short-term price forecast; ensemble empirical mode decomposition; long short-term memory

中图分类号: