A hybrid improved LSTM-CNN model for Chinese stock price trend prediction

Xinyi Xu; Minggang Yang; Heng Liu; Defu Zhang

doi:10.1109/ICCASIT55263.2022.9986705

A hybrid improved LSTM-CNN model for Chinese stock price trend prediction

Xinyi Xu^*, Minggang Yang, Heng Liu, Defu Zhang^*

^*Corresponding author for this work

Xiamen University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Predicting the trend of stock price is a challenging task and good evaluation models can bring huge profits. The classical linear prediction models are not suitable for the stock price trend prediction because the stock market is complex and dynamic. In order to accurately predict the trend of stock price, this paper proposes a hybrid and improved LSTM-CNN stock forecasting model and applied it to predicting the Chinese stock price trend. In addition, we further analyzed the correlation between Chinese stocks and network structure of Chinese stock market. The experimental results show that stocks which belongs to the same sectors influence each other in Chinese stock market, and the LSTM-CNN model has stable accuracy and low risk in the data sets, which shows it has stronger ability to predict stock price trend compared with RF, CNN, and LSTM model. These conclusions can guide investors to make reasonable decisions.

Original language	English
Title of host publication	Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022
Editors	Huabo Sun
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	76-83
Number of pages	8
ISBN (Electronic)	9781665467667
DOIs	https://doi.org/10.1109/ICCASIT55263.2022.9986705
Publication status	Published - 2022
Externally published	Yes
Event	4th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022 - Dali, China Duration: 12 Oct 2022 → 14 Oct 2022

Publication series

Name	Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022

Conference

Conference	4th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022
Country/Territory	China
City	Dali
Period	12/10/22 → 14/10/22

Keywords

Chinese stock
deep learning
stock trend prediction

Access to Document

10.1109/ICCASIT55263.2022.9986705

Cite this

Xu, X., Yang, M., Liu, H., & Zhang, D. (2022). A hybrid improved LSTM-CNN model for Chinese stock price trend prediction. In H. Sun (Ed.), Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022 (pp. 76-83). (Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCASIT55263.2022.9986705

Xu, Xinyi ; Yang, Minggang ; Liu, Heng et al. / A hybrid improved LSTM-CNN model for Chinese stock price trend prediction. Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022. editor / Huabo Sun. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 76-83 (Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022).

@inproceedings{c8780565c02f42079cb47fcebc135e8e,

title = "A hybrid improved LSTM-CNN model for Chinese stock price trend prediction",

abstract = "Predicting the trend of stock price is a challenging task and good evaluation models can bring huge profits. The classical linear prediction models are not suitable for the stock price trend prediction because the stock market is complex and dynamic. In order to accurately predict the trend of stock price, this paper proposes a hybrid and improved LSTM-CNN stock forecasting model and applied it to predicting the Chinese stock price trend. In addition, we further analyzed the correlation between Chinese stocks and network structure of Chinese stock market. The experimental results show that stocks which belongs to the same sectors influence each other in Chinese stock market, and the LSTM-CNN model has stable accuracy and low risk in the data sets, which shows it has stronger ability to predict stock price trend compared with RF, CNN, and LSTM model. These conclusions can guide investors to make reasonable decisions.",

keywords = "Chinese stock, deep learning, stock trend prediction",

author = "Xinyi Xu and Minggang Yang and Heng Liu and Defu Zhang",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022 ; Conference date: 12-10-2022 Through 14-10-2022",

year = "2022",

doi = "10.1109/ICCASIT55263.2022.9986705",

language = "English",

series = "Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "76--83",

editor = "Huabo Sun",

booktitle = "Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022",

address = "United States",

}

Xu, X, Yang, M, Liu, H & Zhang, D 2022, A hybrid improved LSTM-CNN model for Chinese stock price trend prediction. in H Sun (ed.), Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022. Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022, Institute of Electrical and Electronics Engineers Inc., pp. 76-83, 4th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022, Dali, China, 12/10/22. https://doi.org/10.1109/ICCASIT55263.2022.9986705

A hybrid improved LSTM-CNN model for Chinese stock price trend prediction. / Xu, Xinyi; Yang, Minggang; Liu, Heng et al.
Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022. ed. / Huabo Sun. Institute of Electrical and Electronics Engineers Inc., 2022. p. 76-83 (Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A hybrid improved LSTM-CNN model for Chinese stock price trend prediction

AU - Xu, Xinyi

AU - Yang, Minggang

AU - Liu, Heng

AU - Zhang, Defu

PY - 2022

Y1 - 2022

N2 - Predicting the trend of stock price is a challenging task and good evaluation models can bring huge profits. The classical linear prediction models are not suitable for the stock price trend prediction because the stock market is complex and dynamic. In order to accurately predict the trend of stock price, this paper proposes a hybrid and improved LSTM-CNN stock forecasting model and applied it to predicting the Chinese stock price trend. In addition, we further analyzed the correlation between Chinese stocks and network structure of Chinese stock market. The experimental results show that stocks which belongs to the same sectors influence each other in Chinese stock market, and the LSTM-CNN model has stable accuracy and low risk in the data sets, which shows it has stronger ability to predict stock price trend compared with RF, CNN, and LSTM model. These conclusions can guide investors to make reasonable decisions.

AB - Predicting the trend of stock price is a challenging task and good evaluation models can bring huge profits. The classical linear prediction models are not suitable for the stock price trend prediction because the stock market is complex and dynamic. In order to accurately predict the trend of stock price, this paper proposes a hybrid and improved LSTM-CNN stock forecasting model and applied it to predicting the Chinese stock price trend. In addition, we further analyzed the correlation between Chinese stocks and network structure of Chinese stock market. The experimental results show that stocks which belongs to the same sectors influence each other in Chinese stock market, and the LSTM-CNN model has stable accuracy and low risk in the data sets, which shows it has stronger ability to predict stock price trend compared with RF, CNN, and LSTM model. These conclusions can guide investors to make reasonable decisions.

KW - Chinese stock

KW - deep learning

KW - stock trend prediction

UR - http://www.scopus.com/inward/record.url?scp=85146419677&partnerID=8YFLogxK

U2 - 10.1109/ICCASIT55263.2022.9986705

DO - 10.1109/ICCASIT55263.2022.9986705

M3 - Conference contribution

AN - SCOPUS:85146419677

T3 - Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022

SP - 76

EP - 83

BT - Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022

A2 - Sun, Huabo

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022

Y2 - 12 October 2022 through 14 October 2022

ER -

Xu X, Yang M, Liu H, Zhang D. A hybrid improved LSTM-CNN model for Chinese stock price trend prediction. In Sun H, editor, Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 76-83. (Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology, ICCASIT 2022). doi: 10.1109/ICCASIT55263.2022.9986705

A hybrid improved LSTM-CNN model for Chinese stock price trend prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this