Proceedings of the 3rd International Conference on Internet Finance and Digital Economy (ICIFDE 2023)

<Previous Article In Volume
Next Article In Volume>

Stock Price Prediction Based On Neural Networks Incorporating Attention Mechanisms

Authors
XinRui Huang1, *
1School of Economics and Management, Xidian University, Xi’an, China
*Corresponding author. Email: xinrui_huang@outlook.com
Corresponding Author
XinRui Huang
Available Online 29 October 2023.
DOI
10.2991/978-94-6463-270-5_57How to use a DOI?
Keywords
Stock market prediction; RNN; GRU; LSTM; Attention Mechanism
Abstract

Aiming at the nonlinearity of stock prices, this paper first utilizes deep learning neural networks, including Recurrent Neural Network, Long Short-Term Memory and Gated Recurrent Unit, which are known for their strong capability to fit nonlinear function relationships. These networks are used to construct the basic prediction model. Then, the Attention mechanism was introduced to further enhance the model by distinguishing the importance of different information for stock prediction. In this paper, I conduct experimental analysis on the historical stock data of Ping An Bank, spanning a period from from January 4, 2002 to December 30, 2022. Using LSTM, GRU, LSTM-Attention, and GRU-Attention models to predict stock prices. Experimental results show that the GRU model is better than the LSTM model in the three evaluation indexes, and the prediction effect of the model is further improved after adding the attention mechanism. It is proved that the GRU model has a better comprehensive effect, and the attention mechanism is effective and feasible for the optimization of the predictive model.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 3rd International Conference on Internet Finance and Digital Economy (ICIFDE 2023)
Series
Atlantis Highlights in Economics, Business and Management
Publication Date
29 October 2023
ISBN
10.2991/978-94-6463-270-5_57
ISSN
2667-1271
DOI
10.2991/978-94-6463-270-5_57How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - XinRui Huang
PY  - 2023
DA  - 2023/10/29
TI  - Stock Price Prediction Based On Neural Networks Incorporating Attention Mechanisms
BT  - Proceedings of the 3rd International Conference on Internet Finance and Digital Economy (ICIFDE 2023)
PB  - Atlantis Press
SP  - 505
EP  - 514
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-270-5_57
DO  - 10.2991/978-94-6463-270-5_57
ID  - Huang2023
ER  -