%0 Journal Article
%T 基于IndRNN-LSTM模型的股票价格预测
Stock Price Prediction Based on Independently Recurrent Neural Network and Long Short-Term Memory Network
%A 扈文
%J Advances in Applied Mathematics
%P 209-218
%@ 2324-8009
%D 2022
%I Hans Publishing
%R 10.12677/AAM.2022.111026
%X 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.
%K 独立循环神经网络,长短期记忆网络,道琼斯指数
Independently Recurrent Neural Network
%K Long Short-Term Memory Network
%K Dow Jones
Industrial Average
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=48075