Stock Prediction with Stacked-LSTM Neural Networks (2025)

Zhang, X., LI, C., Chen, K.-L., Chrysostomou, D., & Yang, H. (2022). Stock Prediction with Stacked-LSTM Neural Networks. In The 21st IEEE International Conference on Software Quality, Reliability, and Security (QRS-C) (pp. 1119-1125). IEEE (Institute of Electrical and Electronics Engineers). https://doi.org/10.1109/QRS-C55045.2021.00166

@inproceedings{34000074292142568f3b8e17fbb1edf8,

title = "Stock Prediction with Stacked-LSTM Neural Networks",

abstract = "This paper explores a stacked long-term and short-term memory (LSTM) model for non-stationary financial time series in stock price prediction. The proposed LSTM is designed to overcome gradient explosion, gradient vanishing, and save long-term memory. Firstly, build time series with different days for network input, and then add early-stopping, rectified linear units (Relu) activation function to avoid over-fitting during the training stage. Finally, save trained parameters state and new batch size for testing. The results suggest that the developed stacked LSTM produces better predictive power and generalization.",

keywords = "Deep Learning, Stacked Long Short Term Memory, Time Series, neural netowrks, over-fitting, predictive models, software quality, time series analysis",

author = "Xiaochun Zhang and Chen LI and Kuan-Lin Chen and Dimitrios Chrysostomou and Hongji Yang",

year = "2022",

month = apr,

day = "1",

doi = "10.1109/QRS-C55045.2021.00166",

language = "English",

isbn = "978-1-6654-7837-3",

series = "International Conference on Software Quality, Reliability and Security Companion",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

pages = "1119--1125",

booktitle = "The 21st IEEE International Conference on Software Quality, Reliability, and Security (QRS-C)",

address = "United States",

}

Zhang, X, LI, C, Chen, K-L, Chrysostomou, D & Yang, H 2022, Stock Prediction with Stacked-LSTM Neural Networks. in The 21st IEEE International Conference on Software Quality, Reliability, and Security (QRS-C). IEEE (Institute of Electrical and Electronics Engineers), International Conference on Software Quality, Reliability and Security Companion, pp. 1119-1125. https://doi.org/10.1109/QRS-C55045.2021.00166

Stock Prediction with Stacked-LSTM Neural Networks. / Zhang, Xiaochun; LI, Chen; Chen, Kuan-Lin et al.
The 21st IEEE International Conference on Software Quality, Reliability, and Security (QRS-C). IEEE (Institute of Electrical and Electronics Engineers), 2022. p. 1119-1125 (International Conference on Software Quality, Reliability and Security Companion).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Stock Prediction with Stacked-LSTM Neural Networks

AU - Zhang, Xiaochun

AU - LI, Chen

AU - Chen, Kuan-Lin

AU - Chrysostomou, Dimitrios

AU - Yang, Hongji

PY - 2022/4/1

Y1 - 2022/4/1

N2 - This paper explores a stacked long-term and short-term memory (LSTM) model for non-stationary financial time series in stock price prediction. The proposed LSTM is designed to overcome gradient explosion, gradient vanishing, and save long-term memory. Firstly, build time series with different days for network input, and then add early-stopping, rectified linear units (Relu) activation function to avoid over-fitting during the training stage. Finally, save trained parameters state and new batch size for testing. The results suggest that the developed stacked LSTM produces better predictive power and generalization.

AB - This paper explores a stacked long-term and short-term memory (LSTM) model for non-stationary financial time series in stock price prediction. The proposed LSTM is designed to overcome gradient explosion, gradient vanishing, and save long-term memory. Firstly, build time series with different days for network input, and then add early-stopping, rectified linear units (Relu) activation function to avoid over-fitting during the training stage. Finally, save trained parameters state and new batch size for testing. The results suggest that the developed stacked LSTM produces better predictive power and generalization.

KW - Deep Learning

KW - Stacked Long Short Term Memory

KW - Time Series

KW - neural netowrks

KW - over-fitting

KW - predictive models

KW - software quality

KW - time series analysis

UR - http://www.scopus.com/inward/record.url?scp=85140873800&partnerID=8YFLogxK

U2 - 10.1109/QRS-C55045.2021.00166

DO - 10.1109/QRS-C55045.2021.00166

M3 - Article in proceeding

SN - 978-1-6654-7837-3

T3 - International Conference on Software Quality, Reliability and Security Companion

SP - 1119

EP - 1125

BT - The 21st IEEE International Conference on Software Quality, Reliability, and Security (QRS-C)

PB - IEEE (Institute of Electrical and Electronics Engineers)

ER -