文献类型：期刊文献

中文题名：基于改进粒子群算法的LSTM股票预测模型

英文题名：LSTM Stock Prediction Model Based on Improved Particle Swarm Optimization

作者：黄建华[1];钟敏[1];胡庆春[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2022

卷号：48

期号：5

起止页码：696

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：Scopus;北大核心:【北大核心2020】；CSCD:【CSCD_E2021_2022】；

基金：国家高技术研究发展计划(SS2015AA020107)。

语种：中文

中文关键词：LSTM网络;粒子群算法(PSO);股票价格预测;动态调整;特征选择

外文关键词：LSTM network;PSO;stock price prediction;dynamic adjustment;feature selection

摘要：针对LSTM网络中存在的重要参数通常由经验决定,主观性强,或受计算成本影响无法确定最优值,导致模型的拟合能力降低等问题,提出使用改进的粒子群算法优化LSTM网络中的关键参数,减少人为因素影响,优化预测过程,从而构建预测精度更高的股票价格预测模型。该模型通过构建动态多群粒子群优化器来提高粒子群算法的寻优性能,避免出现局部最优。同时,针对股票市场数据维度高、噪声大及数据冗余导致模型训练成本增大、预测性能降低的问题,基于多种特征选择算法构建特征选择模型完成指标特征的过滤筛选,构建完善的预测指标体系。实验结果表明,所提出的股票价格预测模型的准确率得到了明显提高,且具有普遍适用性。
Since LSTM network can effectively deal with time series,it has been widely used to analyze stock prices and future trends.However,the important parameters in the LSTM network are usually determined by experience,which is highly subjective,or the optimal value cannot be determined due to the influence of calculation cost,resulting in the reduction of the fitting ability of the model.Aiming at the above problems,this paper proposes an improved particle swarm algorithm to optimize the key parameters of LSTM network.By reducing the influence of human factors and optimizing the forecasting process,a stock price forecasting model with higher forecasting accuracy is constructed.By utilizing a dynamic multi-swarm particle swarm optimizer to avoid local optimization,the obtained model can improve the optimization performance of PSO algorithm.At the same time,aiming at the problem of high dimension,large noise and data redundancy in the stock market data,which lead to the increase of model training cost and the decrease of prediction performance,a feature selection model is further constructed based on a variety of feature selection algorithms to complete the filtering and screening of index features and build a perfect prediction index system.Finally,it is shown via experimental results that the proposed model can attain higher prediction accuracy and universal applicability in stock price prediction.