In this section, you can access to the latest technical information related to the FUTURE project topic.

Forecasting stock prices with long-short term memory neural network based on attention mechanism

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.

» Author: Jiayu Qiu,  Bin Wang,  Changjun Zhou

» Reference: https://doi.org/10.1371/journal.pone.0227222

» Publication Date: 03/01/2020

» More Information

« Go to Technological Watch



AIMPLAS Instituto Tecnológico del Plástico

C/ Gustave Eiffel, 4
(València Parc Tecnològic) - 46980
PATERNA (Valencia) - SPAIN

PHONE

(+34) 96 136 60 40

EMAIL

Project Management department - Sustainability and Industrial Recovery
life-future-project@aimplas.es