基于主成分分析的LSTM神经网络聚乙烯价格预测研究  

Study on polyethylene price forecast based on principal component analysis and LSTM neural network

作　　者：相广俐 李林[1] Xiang Guangli;Li Lin(School of management,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学管理学院,上海200093

出　　处：《计算机时代》2023年第3期67-70,75,共5页Computer Era

摘　　要：聚乙烯(Polyethylene,PE)是大宗商品中化工产品的重要组成部分,准确预测其价格具有重要意义。使用基于主成分分析的长短期记忆神经网络(PCA-LSTM)模型,实现聚乙烯价格的预测。首先通过Pearson相关性分析对聚乙烯价格影响因素进行研究和选择,其次利用主成分分析对其降维构建影响因素体系,最后建立LSTM神经网络模型进行预测。与SVM、XGBoost模型预测结果做对比,结果表明,该模型对聚乙烯价格的预测效果更好。Polyethylene(PE)is an important component of chemical products in bulk commodities,and accurate forecast of its price is of great significance.In this paper,long short-term memory neural network model based on principal component analysis(PCA-LSTM)is used to realize the forecast of polyethylene price.Firstly,the influencing factors of polyethylene price are studied and selected through Pearson correlation analysis.Secondly,the principal component analysis is used to reduce the dimension and construct the influencing factor system.Finally,the LSTM neural network model is established for forecast.Compared with the forecast results of SVM and XGBoost models,the results show that the model has better forecast effect on polyethylene prices.

关 键 词：价格预测 LSTM神经网络 主成分分析 聚乙烯 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]