基于CEEMDAN与LSTM-Attention的股市预测模型

被引：2

作者：

孙晨宇 ^{[1
]}

张树东 ^{[1
]}

机构：

[1] 首都师范大学信息工程学院

来源：

计算机应用与软件 | 2023年 / 40卷 / 12期

关键词：

LSTM; 经验模态分解; Seq2Seq模型; Attention机制; 股票预测;

D O I：

暂无

中图分类号：

F832.51 []; F224 [经济数学方法];

学科分类号：

020204 ; 0701 ; 070104 ; 1201 ;

摘要：

具有时序特征的金融股票数据有非线性、非平稳和复杂动态的特点，对预测模型提出了挑战。提出一种基于自适应噪声完备集合经验模态分解的LSTM-Attention模型。通过重组后的高频、中频和低频分量，构建更为细化的LSTM-Attention模型，再通过加总合成获得目标预测值。实验结果分析表明，该模型在平均绝对误差(MAE)、均方根误差(RMSE)、均方误差(MSE)和决定系数四个指标上均优于现有模型，有效提升了模型预测的准确率，同时减少了计算开销。

引用

页码：119 / 125 +146

页数：8

共 14 条

[1] Analysis on block chain financial transaction under artificial neural network of deep learning.[J].Wenyou Gao;Chang Su.Journal of Computational and Applied Mathematics.2020, prepublish
[2] Adaptive stock trading strategies with deep reinforcement learning methods.[J].Xing Wu;Haolei Chen;Jianjia Wang;Luigi Troiano;Vincenzo Loia;Hamido Fujita.Information Sciences.2020,
[3] Abstractive social media text summarization using selective reinforced Seq2Seq attention model.[J].Zeyu Liang;Junping Du;Chaoyang Li.Neurocomputing.2020, prepublish
[4] Neural Networks in Narrow Stock Markets
Alfonso, Gerardo
Ramirez, Daniel R.
[J]. SYMMETRY-BASEL, 2020, 12 (08):
[5] Predicting the Trend of Stock Market Index Using the Hybrid Neural Network Based on Multiple Time Scale Feature Learning
Hao, Yaping
Gao, Qiang
[J]. APPLIED SCIENCES-BASEL, 2020, 10 (11):
[6] A Sustainable Quantitative Stock Selection Strategy Based on Dynamic Factor Adjustment
Fu, Yi
Cao, Shuai
Pang, Tao
[J]. SUSTAINABILITY, 2020, 12 (10)
[7] On the forecasting of high-frequency financial time series based on ARIMA model improved by deep learning
Li, Zhenwei
Han, Jing
Song, Yuping
[J]. JOURNAL OF FORECASTING, 2020, 39 (07) : 1081 - 1097
[8] Cascading logistic regression onto gradient boosted decision trees for forecasting and trading stock indices.[J].Feng Zhou;Qun Zhang;Didier Sornette;Liu Jiang.Applied Soft Computing Journal.2019,
[9] Financial time series forecasting model based on CEEMDAN and LSTM.[J].Jian Cao;Zhi Li;Jian Li.Physica A: Statistical Mechanics and its Applications.2018,
[10] Deep learning-based feature engineering for stock price movement prediction.[J].Wen Long;Zhichen Lu;Lingxiao Cui.Knowledge-Based Systems.2018,

← 1 2 →