Development of a Stock Price Prediction Model Integrating LSTM, SVR in Deep Learning and BLS

DOI

10.2991/978-94-6463-540-9_10How to use a DOI?

Keywords

Complete Ensemble Empirical Mode Decomposition; Broad Learning System; Support Vector Regression

Abstract

Stock market aids investors in making wiser choices. However, the complexity and uncertainty of the financial market result in existing prediction models falling short of expectations. Existing Long Short-Term Memory (LSTM) models commonly suffer from lagging issues, while Support Vector Regression (SVR) models tend to overfit. To enhance prediction accuracy, this paper introduces a novel approach that utilizes the advantages of LSTM and SVR separately to handle low-frequency and high-frequency components, respectively, after denoising using Complete Ensemble Empirical Mode Decomposition (CEEMD). By applying Singular Spectrum Analysis (SSA) to remove noise from high-frequency components obtained from CEEMD, prediction precision is improved. Furthermore, Broad Learning System (BLS) is introduced to mitigate the overfitting risk in LSTM, thereby enhancing model stability and generalization capability. This enables the model to excellently predict turning points and high-frequency fluctuations. The effectiveness of the proposed CEEMD-SSA-LSTM-SVR-BLS model in stock price prediction is demonstrated. This comprehensive approach addresses challenges posed by stock market volatility, thereby enhancing the reliability and applicability of stock prediction models. The model proposed in this paper can provide valuable advice to a wide range of investors, offering significant assistance in stock selection and trading decisions.

Copyright

© 2024 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  - Hao Wang
PY  - 2024
DA  - 2024/10/16
TI  - Development of a Stock Price Prediction Model Integrating LSTM, SVR in Deep Learning and BLS
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 76
EP  - 86
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_10
DO  - 10.2991/978-94-6463-540-9_10
ID  - Wang2024
ER  -