Applying Deep Learning to Financial Market: Stock Return Prediction and Investment Portfolio Construction

DOI

10.2991/978-94-6463-742-7_10How to use a DOI?

Keywords

Long Short-Term Memory; Correlation Coefficient; Root Mean Square Error; Deep Learning; Stock price prediction

Abstract

The next day’s closing cost of the S&P 500 indicator is used in this study’s forecasting. A particular neural network style is known as a Long Short-Term Memory (LSTM) system. It employs eleven voting machines, a healthy ensemble, and incorporates important business data, macroeconomic data, and technical indicators to get a complete list of share market activities. Both single and dual studies are developed. And several LSTM types, which are evaluated utilizing Root Mean Square Error. The Correlation Coefficient (R²) and (RMSE) are both present. The ensemble’s performance is demonstrated by the benefits. In terms of prediction precision, the LSTM model outperforms individual models. Moreover, making use of the study projections property based on the consensus of LSTM types to determine levels. Applying a binary classification method based on the middle, the business performed. Profits. When applied to the Stockholm SPX500, the ensemble type demonstrates. Better portfolio forecasting performance, greater daily returns, and better daily returns. Compared to full-index and random-ratio, both have lower volatility and cumulative returns assets.

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  - Jiayu Duan
AU  - Xuan Zheng
PY  - 2025
DA  - 2025/05/31
TI  - Applying Deep Learning to Financial Market: Stock Return Prediction and Investment Portfolio Construction
BT  - Proceedings of the 2025 4th International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2025)
PB  - Atlantis Press
SP  - 80
EP  - 91
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-742-7_10
DO  - 10.2991/978-94-6463-742-7_10
ID  - Duan2025
ER  -