Forecasting stock prices with long-short term memory neural network based on attention mechanism.
PLoS One
; 15(1): e0227222, 2020.
Article
em En
| MEDLINE
| ID: mdl-31899770
ABSTRACT
The stock market is known for its extreme complexity and volatility, and people are always looking for an accurate and effective way to guide stock trading. Long short-term memory (LSTM) neural networks are developed by recurrent neural networks (RNN) and have significant application value in many fields. In addition, LSTM avoids long-term dependence issues due to its unique storage unit structure, and it helps predict financial time series. Based on LSTM and an attention mechanism, a wavelet transform is used to denoise historical stock data, extract and train its features, and establish the prediction model of a stock price. We compared the results with the other three models, including the LSTM model, the LSTM model with wavelet denoising and the gated recurrent unit(GRU) neural network model on S&P 500, DJIA, HSI datasets. Results from experiments on the S&P 500 and DJIA datasets show that the coefficient of determination of the attention-based LSTM model is both higher than 0.94, and the mean square error of our model is both lower than 0.05.
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Redes Neurais de Computação
/
Comércio
Tipo de estudo:
Health_economic_evaluation
/
Prognostic_studies
Limite:
Humans
Idioma:
En
Ano de publicação:
2020
Tipo de documento:
Article