MCI-GRU: Stock prediction model based on multi-head cross-attention and improved GRU

Peng Zhu, Yuante Li, Yifan Hu, Sheng Xiang, Qinyuan Liu, Dawei Cheng, Yuqi Liang

Abstract: Highlights•This paper improves the GRU by replacing the reset gate with an attention mechanism.•We propose a multi-head cross-attention to learn and integrate market latent states.•Empirical studies show the method outperforms the latest existing approaches.