现代计算机2024，Vol.30Issue(22) ：67-72.DOI:10.3969/j.issn.1007-1423.2024.22.011

基于小波去噪和长短期记忆网络的聚丙烯价格预测

Polypropylene price prediction based on wavelet denoising and long short term memory networks

陈孝文 苏攀 王欣宇 张新香
现代计算机2024，Vol.30Issue(22) ：67-72.DOI:10.3969/j.issn.1007-1423.2024.22.011
✕
  • 万方数据

基于小波去噪和长短期记忆网络的聚丙烯价格预测

Polypropylene price prediction based on wavelet denoising and long short term memory networks

陈孝文 1苏攀 1王欣宇 2张新香2
扫码查看

作者信息

  • 1. 湖北中烟工业有限责任公司,武汉 430040
  • 2. 中南财经政法大学信息工程学院,武汉 430073
  • 折叠

摘要

为帮助烟草企业更好地控制生产成本,科学制定采购价格,利用小波去噪和长短期记忆网络(LSTM)模型预测烟用薄膜上游主要原材料聚丙烯的价格.首先,借助小波分析对聚丙烯期货数据实施去噪;然后,构建LSTM模型,并与ARIMA、MLP以及RNN模型展开对比;最后,选取多组特征组合,利用预测精度最高的LSTM模型开展预测.结果表明,小波分析去噪法处理金融数据噪音的可靠性强,基于小波分析去噪后的收盘价、最大值及最小值特征组合的LSTM模型预测效果最优.

Abstract

In order to help tobacco enterprises control production cost better and make purchase price scientifically,this paper uses wavelet denoising and long short term memory network(LSTM)model to predict the price of polypropylene,the main raw mate-rial upstream of tobacco film.Firstly,using wavelet analysis to denoise polypropylene futures data.Then,an LSTM model was con-structed and compared with ARIMA,MLP,and RNN models.Finally,using LSTM model and selecting multiple sets of feature com-binations for price prediction.The results show that the effect of LSTM model prediction based on the combination of closing price,maximum value and minimum value after wavelet analysis is optimal,and wavelet analysis denoising method in dealing with finan-cial data noise is verified to be valid.

关键词

长短期记忆网络/价格预测/小波分析/聚丙烯期货

Key words

long short-term memory network/price prediction/wavelet analysis/polypropylene futures

引用本文复制引用

出版年

2024
现代计算机
中大控股

现代计算机

影响因子：0.292
ISSN：1007-1423
段落导航相关论文