Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)

<Previous Article In Volume
Next Article In Volume>

Long Short-Term Memory Neural Network for Different Regional Financial Time Series

Authors
Yexuan Weng1, Guanming Su2, Hanyu Chen3, *, Rong Huang4
1Business College, Wenzhou-Kean University, Wenzhou, 325060, China
2Beijing-Dublin International College at BJUT, Beijing University of Technology, Beijing, 100124, China
3Tianmu College, Zhejiang Agricultural and Forestry University, Zhejiang, 311800, China
4Miami University, Oxford, 45011, USA
*Corresponding author. Email: erichanhy95@gmail.com
Corresponding Author
Hanyu Chen
Available Online 31 May 2025.
DOI
10.2991/978-94-6463-742-7_19How to use a DOI?
Keywords
Long Short-Term Memory (LSTM); Financial Forecasting; Stock Price Prediction; DAX30 Index; Deep Learning
Abstract

Recent advancements in machine learning, particularly deep learning, have transformed financial forecasting by addressing complex, non-linear, and non-stationary financial data. This study digs into the predictive capabilities of Long Short-Term Memory (LSTM) networks, focusing on the German DAX30 index but not missing out on the analysis of other prominent indices, such as the DJIA and S&P 500. We trained an ensemble of 110 LSTM models on historical stock data to capture intricate temporal patterns and long-term trends. The results indicate that the LSTM ensemble works better than the traditional methods, having higher cumulative returns, lower volatility, and higher risk-adjusted performance. Although there are limitations during high-volatility periods, the findings demonstrate the robustness of LSTM models across different market conditions. This research also proposes potential improvements, including integrating hybrid models and refined trading strategies in terms of financial forecasting.

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)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)
Series
Advances in Intelligent Systems Research
Publication Date
31 May 2025
ISBN
978-94-6463-742-7
ISSN
1951-6851
DOI
10.2991/978-94-6463-742-7_19How to use a DOI?
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.

Cite this article

risenwbib
TY  - CONF
AU  - Yexuan Weng
AU  - Guanming Su
AU  - Hanyu Chen
AU  - Rong Huang
PY  - 2025
DA  - 2025/05/31
TI  - Long Short-Term Memory Neural Network for Different Regional Financial Time Series
BT  - Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)
PB  - Atlantis Press
SP  - 166
EP  - 174
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-742-7_19
DO  - 10.2991/978-94-6463-742-7_19
ID  - Weng2025
ER  -