Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism
By Chang Zong, Jian Shao, Weiming Lu, Yueting Zhuang
Rating
1383
Battle Count: 100
Relevance
9/10
Highly relevant for developing advanced stock prediction models that integrate multiple data sources
Implementation Complexity
7/10
Requires implementation of complex neural network architectures and handling of multiple data modalities
Reproducibility
4/5
The paper provides detailed methodology and experimental setup. Code and datasets are available.
About this paper
Methodology: Multimodal Stable Fusion with Gated Cross-Attention (MSGCA). Problem types: Classification, Time Series Forecasting.
The interactive Everscope explorer (charts, battles, favorites) loads below.