Analysis and Research on Stock Price of LSTM and Bidirectional LSTM Neural Network

DOI

10.2991/iccia-19.2019.72How to use a DOI?

Keywords

Bidirectional long-short term memory network; over-fitting; long-short term memory network; deviation error; stock price.

Abstract

The stock market has the characteristics of large fluctuations and high dimensions, and can be regarded as a nonlinear time series system, so the traditional time series method is not applicable. For the study of deep learning methods, this paper proposed a bidirectional long-short term memory (BLSTM) neural network. Compared with ARIMA model and LSTM neural network, the (BLSTM) neural network is used to predict the accuracy of GREE stock price. Firstly, the stock data is normalized and pre-processing, and then the processed data is input into one-way and two-way LSTM respectively. In the neural network, Dropout is used as an optimization term to prevent over-fitting of the network, and then the three evaluation criteria of RMSE, MAE and Loss are selected to comprehensively analyze the rationality of a single bidirectional LSTM neural network. The experimental results show that the RMSE and MAE are reduced by about 24.2% and 19.4% respectively, and the deviation accuracy is increased by 0.13%. The network complexity is not high, and the error is effectively reduced. It can provide reference value for short-term market investors.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Mingzhu Jia
AU  - Jian Huang
AU  - Lihua Pang
AU  - Qian Zhao
PY  - 2019/07
DA  - 2019/07
TI  - Analysis and Research on Stock Price of LSTM and Bidirectional LSTM Neural Network
BT  - Proceedings of the 3rd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2019)
PB  - Atlantis Press
SP  - 467
EP  - 473
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-19.2019.72
DO  - 10.2991/iccia-19.2019.72
ID  - Jia2019/07
ER  -