Open access
Aug 2026
A Stock Market Price Prediction Model Integrating a CNN–Transformer Dual-Channel Dynamic Attention Architecture
A CNN–Transformer dual-channel architecture equipped with a dynamic attention fusion module for stock price forecasting that reduces mean absolute error and root mean square error and remains effective across markets with differing volatility profiles is introduced.
Chengcheng Han, Jing-Wei Guo, Xingyu Feng
· Mathematics · 0 citations