Paper: arXiv 2406.06594
Authors: Chang Zong, Hang Zhou
Abstract
The accurate prediction of stock movements is crucial for investment strategies. Stock prices are subject to the influence of various forms of information, including financial indicators, sentiment analysis, news documents, and relational structures. Predominant analytical approaches, however, tend to address only unimodal or bimodal sources, neglecting the complexity of multimodal data. Further complicating the landscape are the issues of data sparsity and semantic conflicts between these modalities, which are frequently overlooked by current models, leading to unstable performance and limiting practical applicability. To address these shortcomings, this study introduces a novel architecture, named Multimodal Stable Fusion with Gated Cross-Attention (MSGCA), designed to robustly integrate multimodal input for stock movement prediction. The MSGCA framework consists of three integral components: (1) a trimodal encoding module, responsible for processing indicator sequences, dynamic documents, and a relational graph, and standardizing their feature representations; (2) a cross-feature fusion module, where primary and consistent features guide the multimodal fusion of the three modalities via a pair of gated cross-attention networks; and (3) a prediction module, which refines the fused features through temporal and dimensional reduction to execute precise movement forecasting. Empirical evaluations demonstrate that the MSGCA framework exceeds current leading methods, achieving performance gains of 8.1%, 6.1%, 21.7% and 31.6% on four multimodal datasets, respectively, attributed to its enhanced multimodal fusion stability.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper involves advanced deep learning architectures (Gated Cross-Attention, GAT, LLMs) and complex multimodal fusion mathematics, while demonstrating strong empirical validation with specific performance metrics (8.1%, 6.1%, etc. gains) across four real multimodal datasets, indicating backtest-ready methodology.
Research Flowchart
flowchart TD
A["Research Goal:<br>Predict Stock Movements<br>from Multimodal Data"] --> B["Key Data Inputs"]
subgraph B
B1["Financial Indicators"]
B2["News & Social Media"]
B3["Relational Graphs"]
end
B --> C["MSGCA Architecture"]
subgraph C ["Computational Process"]
C1["Trimodal Encoding<br>Feature Standardization"]
C2["Cross-Feature Fusion<br>Gated Cross-Attention"]
C3["Prediction Module<br>Temporal Reduction"]
end
C1 --> C2 --> C3
C3 --> D["Key Findings"]
subgraph D ["Outcomes"]
D1["SOTA Performance<br>+8.1% to +31.6% improvement"]
D2["Enhanced Stability<br>Solves semantic conflicts"]
D3["Robust Fusion<br>Overcomes data sparsity"]
end
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes MSGCA, a multimodal stable fusion architecture with gated cross‑attention for fine‑grained stock movement prediction.
Source sentence
this study introduces a novel architecture, named Multimodal Stable Fusion with Gated Cross-Attention (MSGCA), designed to robustly integrate multimodal input for stock movement prediction.
Assumes
No explicit assumptions found in the text.
Data
- InnoStock text-news unknown
Source sentence
InnoStock, originally collected by us from CSMAR 5, focuses on newly formed technology companies listed on China’s Sci‑Tech Innovation Board, aggregating their financial news from various online platforms.
- BigData22 text-news public
Source sentence
of high‑trade‑volume stocks in US stock markets and dynamic input from tweets and price sequences.
- ACL18 text-news public
Source sentence
of high‑trade‑volume stocks in US stock markets and dynamic input from tweets and price sequences.
- CIKM18 text-news public
Source sentence
of high‑trade‑volume stocks in US stock markets and dynamic input from tweets and price sequences.
CSMAR
Costs
Not applicable
Finds 2
- MSGCA outperforms leading baselines by margins of 8.1%, 6.1%, 21.7% and 31.6% on the four multimodal datasets respectively. performance
Source sentence
our MSGCA model outperforms these baselines by margins of 8.1%, 6.1%, 21.7%, and 31.6% on four datasets, respectively.
- MSGCA consistently achieves the best performance on all datasets and metrics for fine‑grained stock movement prediction. performance
Source sentence
Our MSGCA consistently achieves the best performance on all datasets and metrics.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 7 related papers). Coverage is partial, so this is neither replication nor refutation.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.