Adaptive Decomposition and Dual-Branch Linear Forecasting for Stock Price Prediction
- 1School of Information Management, Central China Normal University, Wuhan 430079, China
- 2School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100190, China
Abstract
Stock price forecasting is important for financial decision-making but remains challenging because of complex and volatile market dynamics. Although existing forecasting methods have achieved considerable progress, they still face several limitations. Decomposition-based approaches are sensitive to manually specified parameters, deep learning models often require high computational resources, and individual lightweight models may not adequately capture diverse temporal characteristics. To address these limitations, this study proposes an improved whale optimization-based variational mode decomposition and dual-branch normalized linear forecasting (IWVMD-DNFLinear) framework, which integrates adaptive sequence decomposition, complementary linear forecasting, and learnable fusion. An improved beluga whale optimization (IBWO) algorithm is employed to adaptively optimize the parameters of variational mode decomposition (VMD). The decomposed components are then processed by parallel decomposition-based linear forecasting (DLinear) and normalized linear forecasting (NLinear) branches with a learnable fusion mechanism. Extensive experiments on four stock datasets under multiple forecasting horizons demonstrate that IWVMD-DNFLinear achieves consistently competitive forecasting performance against the trained baseline models across different datasets and forecasting horizons. On the AAPL dataset under single-step forecasting, IWVMD-DNFLinear achieves the lowest root mean square error (RMSE) of 5.1220. The DNFLinear forecasting network contains only 743 trainable parameters and requires 0.0110 MB of model storage. The proposed framework achieves high forecasting accuracy while maintaining a parameter-efficient forecasting structure, providing a practical solution for stock price forecasting.
Related
- Volatility-Corrected Prediction Intervals: Locally Adaptive Uncertainty Quantification for Probabilistic Time-Series Forecasting
- DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting
- A Decomposition-Based Data-Driven Branch-and-Bound Approach for Black-Box Global Optimization
- Hankel-Koopman Finite-Horizon Energy Decomposition of Coupled Experimental Data: A Three-Phase Data-Driven Twin Forecasting Framework
- Conditional Decomposition Discrepancy: Separating Conditional Bias from Sampling Bias in Small-Sample Cross-Domain Cost Forecasting
BibTeX
@article{xiao2026adaptive,
title = {{Adaptive Decomposition and Dual-Branch Linear Forecasting for Stock Price Prediction}},
author = {Yi Xiao and Genfan Huang and Chen He and Tianxiao Song and Yi Hu},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14193622},
url = {https://www.mdpi.com/2227-7390/14/19/3622},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Adaptive Decomposition and Dual-Branch Linear Forecasting for Stock Price Prediction
AU - Yi Xiao
AU - Genfan Huang
AU - Chen He
AU - Tianxiao Song
AU - Yi Hu
PY - 2026
DA - 2026/10/07
JO - Mathematics
DO - 10.3390/math14193622
UR - https://www.mdpi.com/2227-7390/14/19/3622
AB - Stock price forecasting is important for financial decision-making but remains challenging because of complex and volatile market dynamics. Although existing forecasting methods have achieved considerable progress, they still face several limitations. Decomposition-based approaches are sensitive to manually specified parameters, deep learning models often require high computational resources, and individual lightweight models may not adequately capture diverse temporal characteristics. To address these limitations, this study proposes an improved whale optimization-based variational mode decomposition and dual-branch normalized linear forecasting (IWVMD-DNFLinear) framework, which integrates adaptive sequence decomposition, complementary linear forecasting, and learnable fusion. An improved beluga whale optimization (IBWO) algorithm is employed to adaptively optimize the parameters of variational mode decomposition (VMD). The decomposed components are then processed by parallel decomposition-based linear forecasting (DLinear) and normalized linear forecasting (NLinear) branches with a learnable fusion mechanism. Extensive experiments on four stock datasets under multiple forecasting horizons demonstrate that IWVMD-DNFLinear achieves consistently competitive forecasting performance against the trained baseline models across different datasets and forecasting horizons. On the AAPL dataset under single-step forecasting, IWVMD-DNFLinear achieves the lowest root mean square error (RMSE) of 5.1220. The DNFLinear forecasting network contains only 743 trainable parameters and requires 0.0110 MB of model storage. The proposed framework achieves high forecasting accuracy while maintaining a parameter-efficient forecasting structure, providing a practical solution for stock price forecasting.
SN - 2227-7390
ER -