Accurate and efficient stock market index prediction: an integrated approach based on VMD-SNNs

Xuchang Chen, Guoqiang Tang, Yumei Ren, Xin Lin and Tongzhi Li

Journal of Applied Statistics, 2025, vol. 52, issue 4, 841-867

Abstract: The stock market index typically mirrors the financial market's performance. Hence, accurate prediction of stock market index trends is essential for investors aiming to mitigate financial risk and enhance future investment returns. Traditional statistical approaches often struggle with the non-linear nature of stock market index data, leading to potential inaccuracies in long-term predictions. To address this issue, we introduce the TCN-LSTM-SNN (TLSNN) model, a hybrid framework that integrates Long Short-Term Memory (LSTM) and Temporal Convolutional Network (TCN) for robust feature extraction, within a highly efficient Spiking Neural Network (SNN) architecture. Additionally, we employ the Subtraction-Average-Based Optimizer (SABO) to refine the Variational Mode Decomposition (VMD) technique, thereby separating the periodic and trend components of stock indices, reducing noise interference, and establishing a decomposition ensemble framework to bolster the model's resilience. The experimental results show that the VMD-TLSNN hybrid model suggested in this study surpasses other individual benchmark models and their hybrid models in prediction accuracy. Additionally, it demonstrates notably lower energy consumption compared to other hybrid models.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664763.2024.2395961 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:52:y:2025:i:4:p:841-867

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664763.2024.2395961

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().