RF-MIP-LSTM股价预测模型

doi:10.3778/j.issn.1002-8331.2312-0329

摘要/Abstract

摘要： 长短时记忆（LSTM）神经网络在预测股价波动这类复杂的非线性系统中展现了较好的性能，然而LSTM模型没有考虑三个门控机制的耦合关系和长时记忆对模型输入的影响。通过增加输入门控的长时记忆窥视和耦合了三个门控机制的唯一门机制，增强了长时记忆信息传递和模型的稳定性，构建了基于随机森林特征选择的RF-MIP-LSTM模型，并推导了模型的前向与反向传播算法。通过对中国农业银行、盐田港、格力电器三只股票价格和上证指数的预测和比较，表明RF-MIP-LSTM模型的收敛速度和预测精度均优于LSTM模型。

关键词: 股价预测, 随机森林（RF）, 长短时记忆（LSTM）神经网络, 长时窥视孔

Abstract: Long short-term memory (LSTM) neural networks have demonstrated superior performance in predicting complex nonlinear systems such as stock price fluctuations. However, the traditional LSTM models do not take into account the coupling relationships among the three gating mechanisms and the impact of long-term memory on the model’s input. This paper enhances the transmission of long-term memory peeking information and the stability of the model by incorporating long-term memory into the input gate and coupling the three gating mechanisms into a unique gate mechanism. It constructs an LSTM model based on feature selection with random forest (RF-MIP-LSTM) and derives the forward and backward propagation algorithms for the model. Through predictions and comparisons on stock prices of Agricultural Bank of China, Yantian Port, Gree Electric Appliances, and the Shanghai Stock Exchange Index, the RF-MIP-LSTM model exhibits superior convergence speed and predictive accuracy compared to the traditional LSTM model.

Key words: stock price prediction, random forest (RF), long short-term memory (LSTM) neural network, long peephole

张颖, 李路. RF-MIP-LSTM股价预测模型[J]. 计算机工程与应用, 2024, 60(17): 272-281.

ZHANG Ying, LI Lu. RF-MIP-LSTM Stock Price Prediction Model[J]. Computer Engineering and Applications, 2024, 60(17): 272-281.

参考文献

[1] 于海姝, 蔡吉花, 夏红. ARIMA模型在股票价格预测中的应用[J]. 经济师, 2015(11): 156-157.
YU H S, CAI J H, XIA H. Application of ARIMA model in stock price forecasting[J]. China Economist, 2015(11): 156-157.
[2] LI B, ZHANG J, CHEN Q. Quantitative nondestructive testing of steel wire rope based on optimized support vector machine[J]. Russian Journal of Nondestructive Testing, 2021, 57(11): 1008-1017.
[3] GURESEN E, KAYAKUTLU G, DAIM T U. Using artificial neural network models in stock market index prediction[J]. Expert Systems with Applications, 2011, 38(8): 10389-10397.
[4] 隋金城. 遗传算法优化BP神经网络的股价预测研究[J]. 经济技术协作信息, 2020(7): 55.
SUI J C. Research on the prediction of stock prices using genetic algorithm optimized BP neural network [J]. Economic and Technical Cooperation Information, 2020(7): 55.
[5] 吕琦. 基于SVM的股票时间序列的预测研究[J]. 吉林工程技术师范学院学报, 2011(7): 48-49.
LYU Q. Research on stock time series forecasting based on SVM[J]. Journal of Jilin Engineering Normal University, 2011(7): 48-49.
[6] SAMARAWICKRAMA A J P, FERNANDO T G I. A recurrent neural network approach in predicting daily stock prices an application to the Sri Lankan stock market[C]//Proceedings of the 2017 IEEE International Conference on Industrial and Information Systems, 2017: 1-6.
[7] LIU Y, GUAN L, HOU C, et al. Wind power short-term prediction based on LSTM and discrete wavelet transform[J]. Applied Sciences, 2019, 9(6): 1108.
[8] KUMAR K, HAIDER M T U. Enhanced prediction of intra-day stock market using metaheuristic optimization on RNN-LSTM network[J]. New Generation Computing, 2021, 39(1): 231-272.
[9] 左川, 王宇, 李振. 深度学习在股票投资中的应用[J]. 郑州大学学报 (哲学社会科学版), 2022, 55(2): 56-62.
ZUO C, WANG Y, LI Z. Application of deep learning in stock investment[J]. Journal of Zhengzhou University (Philosophy and Social Sciences), 2022, 55(2): 56-62.
[10] 陈卫华, 徐国祥. 基于深度学习和股票论坛数据的股市波动率预测精度研究[J]. 管理世界, 2018, 34(1): 180-181.
CHEN W H, XU G X. Research on the prediction accuracy of stock market volatility based on deep learning and stock forum data [J]. Management World, 2018, 34(1): 180-181.
[11] 包志强, 赵研, 胡啸天, 等. 最小窥视孔长短时记忆模型[J]. 计算机工程与设计, 2020, 41(1): 134-138.
BAO Z Q, ZHAO Y, HU X T, et al. Minimal peephole long short-term memory model[J]. Computer Engineering and Design, 2020, 41(1): 134-138.
[12] 蔡鑫祥, 撖奥洋, 周生奇, 等. 基于改进Bagging算法与模糊MP-LSTM融合的短期负荷预测模型[J]. 电气工程学报, 2022, 17(1): 164-170.
CAI X X, YAN A Y, ZHOU S Q, et al. A short-term load forecasting model based on improved bagging algorithm and fuzzy MP-LSTM integration[J]. Journal of Electrical Engineering, 2022, 17(1): 164-170.
[13] 蔡鑫祥. 基于MP-RLSTM的电力系统短期负荷预测研究[D]. 青岛: 青岛大学, 2022.
CAI X X. Research on short-term load forecasting of power systems based on MP-RLSTM[D]. Qingdao: Qingdao University, 2022.
[14] HU J, ZHENG W D. Transformation-gated LSTM: efficient capture of short-term mutation dependencies for multivariate time series prediction tasks[C]//Proceedings of the 2019 International Joint Conference on Neural Networks, 2019: 1-8.
[15] 刘玉敏, 李洋, 赵哲耘. 基于特征选择的RF-LSTM模型成分股价格趋势预测[J]. 统计与决策, 2021, 37(1): 157-160.
LIU Y M, LI Y, ZHAO Z Y. Stock trend prediction of component stocks based on feature selection and RF-LSTM model[J]. Statistics and Decision, 2021, 37(1): 157-160.
[16] 李辉, 化金金, 邹波蓉. 基于RF-LSTM组合模型的股票价格预测[J]. 河南理工大学学报 (自然科学版), 2022, 41(1): 136-142.
LI H, HUA J J, ZOU B R. Stock price prediction based on the RF-LSTM combined model [J]. Journal of Henan Polytechnic University (Natural Science Edition), 2022, 41(1): 136-142.
[17] 邹婕, 李路. RF-SA-GRU模型的股价预测研究[J]. 计算机工程与应用, 2023, 59(15): 300-309.
ZOU J, LI L. Research on stock price prediction using the RF-SA-GRU model[J]. Computer Engineering and Applications, 2023, 59(15): 300-309.
[18] 方义秋, 卢壮, 葛君伟. 联合RMSE损失LSTM-CNN模型的股价预测[J]. 计算机工程与应用, 2022, 58(9): 294-302.
FANG Y Q, LU Z, GE J W. Stock price forecasting based on combined RMSE loss LSTM-CNN model[J]. Computer Engineering and Applications, 2022, 58(9): 294-302.