A Hybrid CNN-LSTM Model for Industry-Level Stock Price Prediction

DOI

10.2991/978-94-6463-845-5_69How to use a DOI?

Keywords

Stock Price Prediction; Convolutional Neural Network; Long-Short-Term Memory Neural Network; Industry-Level

Abstract

Due to the rapid price fluctuations in the stock market, traditional stock price prediction methods struggle to achieve satisfactory prediction performance. We use the CNN-LSTM model to predict stock prices at the industry level in this paper. The data used in this paper come from the first-level industries of the Shenwan classification, covering the period from January 4, 2000, to April 1, 2025. It consists of 5612 samples and the last 500 samples are selected as the test set. The dataset includes eight features: opening price, highest price, lowest price, closing price, trading volume, price change, percentage change, and turnover rate. We use three evaluation methods: MAE, RMSE, and R² to compare the results with DNN, CNN, and LSTM. It was found that the CNN-LSTM model had the best prediction performance. The methods and results in this paper can provide references and insights for investors to conduct research and make allocations in the A-share market from an industry level.

Copyright

© 2025 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  - Jiancheng Gao
PY  - 2025
DA  - 2025/09/16
TI  - A Hybrid CNN-LSTM Model for Industry-Level Stock Price Prediction
BT  - Proceedings of the 2025 6th International Conference on Management Science and Engineering Management (ICMSEM 2025)
PB  - Atlantis Press
SP  - 679
EP  - 690
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-845-5_69
DO  - 10.2991/978-94-6463-845-5_69
ID  - Gao2025
ER  -