|
|
基于IndRNN-LSTM模型的股票价格预测
|
Abstract:
结合独立循环神经网络和长短期记忆网络建立IndRNN-LSTM模型，选取道琼斯指数的18个指标，对道琼斯指数的开盘价格进行预测。另外，分别采用CNN-LSTM、IndRNN、LSTM、SVM、BP和CNN神经网络模型对开盘价格进行预测，并将七种模型的预测结果进行比较，结果表明IndRNN-LSTM模型的预测精度较高，能更好地预测股票的走势。
IndRNN-LSTM model is established by combining independently recurrent neural network and long short-term memory network. This paper selects 18 indexes of Dow Jones index to predict the opening price of Dow Jones index. CNN-LSTM, IndRNN, SVM and LSTM neural network models are also used to predict the opening price, and the prediction results of the five models are compared. The results show that the IndRNN-LSTM model has high prediction accuracy and can better predict the stock trend.
| [1] | 周阳. 基于LSTM模型的上证综指价格预测研究[D]: [硕士学位论文]. 南京: 南京邮电大学, 2019. |
| [2] | 赵浩博, 李锡祚. 基于卷积和循环神经网络模型融合的股票开盘价预测研究[J]. 智能计算机与应用, 2019, 9(6): 55-58+64. |
| [3] | 钱赟. 基于主成分分析与序列到序列学习模型的股票收盘价格预测[D]: [硕士学位论文]. 上海: 上海师范大学, 2020. |
| [4] | 王东, 王霄鹏, 杨川东. 一种基于主成分LSTM模型在股票预测中的研究[J]. 重庆理工大学学报(自然科学), 2021, 35(2): 282-288. |
| [5] | 黄超斌, 程希明. 基于LSTM神经网络的股票价格预测研究[J]. 北京信息科技大学学报(自然科学版), 2021, 36(1): 79-83. |
| [6] | 王玉堃. LSTM和GRU神经网络在股指高频数据预测中的研究[D]: [硕士学位论文]. 济南: 山东大学, 2020. |
| [7] | Li, S., Li, W., Cook, C., et al. (2018) Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 5457-5466. https://doi.org/10.1109/CVPR.2018.00572 |
