CNN-BiLSTM-Attention Algorithm-Based Stock Prices Prediction During COVID-19

DOI

10.2991/978-94-6463-512-6_47How to use a DOI?

Keywords

CNN-LSTM-Attention; LSTM; stock price prediction

Abstract

Stocks play a crucial role in the field of financial investment, and achieving more accurate stock price predictions is a key focus for today's investors and scholars. However, current algorithms predominantly focus on stable periods and are somewhat inadequate in studying stock price trends during exceptional periods, such as the COVID-19 pandemic and financial crises. Therefore, this paper focuses on stock price prediction during the COVID-19 pandemic. Centered on the LSTM algorithm, it employs CNN for feature extraction and introduces BiLSTM and Attention mechanisms to further enhance model robustness. By constructing a CNN-BiLSTM-Attention composite model, the paper achieves predictions for the stock prices of SZ002912, SZ300006, and SS603311 from different sectors. The study finds that the prediction accuracy of the CNN-BiLSTM-Attention model is significantly higher than that of the standard LSTM model, as it better captures short-term stock price fluctuations. However, it fails to provide effective warnings to investors in the event of sudden, sharp declines in stock prices, unlike the LSTM model.

Copyright

© 2024 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)

TY  - CONF
AU  - Xiaoshuai Wang
PY  - 2024
DA  - 2024/09/23
TI  - CNN-BiLSTM-Attention Algorithm-Based Stock Prices Prediction During COVID-19
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 441
EP  - 452
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_47
DO  - 10.2991/978-94-6463-512-6_47
ID  - Wang2024
ER  -