摘要
针对股票预测模型存在时效性和预测功能单一化的问题,本文在长短期记忆网络(LSTM)的基础上,提出了融合自注意力机制(SA)和时间卷积网络(TCN)的双向长短期记忆(BiLSTM)神经网络(BiLSTM-SA-TCN)股票预测模型.BiLSTM-SA-TCN模型中的学习单元和预测单元可以有效学习重要的股票数据,同时能够抓取长时间的依赖信息,输出次日股票收盘价预测值.实验结果表明,BiLSTM-SA-TCN模型在多个数据集上的预测结果更加稳定,模型泛化能力较高,在对比实验中,BiLSTM-SA-TCN模型在大部分数据集上均方根误差最小,平均绝对值误差最小,拟合度R^(2)最优.
To address the poor timeliness and simple prediction functions of stock forecasting models,we propose a model abbreviated as BiLSTM-SA-TCN,which combines Bi-directional Long Short-Term Memory(Bi-LSTM)neural network,Self-Attention(SA)and Temporal Convolution Network(TCN).The learning unit and prediction unit in the proposed model can effectively learn important stock data,capture long-term dependency information,and output the predicted next day close price.The experimental results indicate that the BiLSTM-SA-TCN model has more stable prediction results on multiple data sets and has higher modle generalization ability.Furthormore,incomparative experiment,the BiLSTM-SA-TCN model achieves the lowest root mean square error,the lowest mean absolute error,and the best fitting degree of R^(2) on the majority of datasets.
作者
杨智勇
叶玉玺
周瑜
YANG Zhiyong;YE Yuxi;ZHOU Yu(Big Data and Internet of Things School,Chongqing Vocational Institute of Engineering,Chongqing 402260,China;College of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China;College of Finance and Tourism,Chongqing Vocational Institute of Engineering,Chongqing 402260,China)
出处
《南京信息工程大学学报（自然科学版）》
CAS
北大核心
2023年第6期643-651,共9页
Journal of Nanjing University of Information Science & Technology（Natural Science Edition）
基金
重庆市自然科学基金(cstc2021ycjh-bgzxm0088)
重庆市教育委员会科学技术研究计划项目(KJQN201903402)。
关键词
股票价格预测
长短期记忆网络
注意力机制
时间卷积网络
stock price forecast
long short-term memory(LSTM)
attention mechanism
temporal convolution network(TCN)
