MSMF: Multi-Scale Multi-Modal Fusion for Enhanced Stock Market Prediction

TL;DR

MSMF introduces a multi-scale, multi-modal fusion framework that significantly improves stock market prediction accuracy by effectively integrating heterogeneous data types and preserving multi-granularity features.

Contribution

The paper proposes a novel multi-scale multi-modal fusion approach with innovative mechanisms like Multi-Granularity Gates and task-targeted prediction for enhanced stock forecasting.

Findings

MSMF outperforms existing models in accuracy.

Reduces prediction errors across tasks.

Effectively integrates diverse financial data modalities.

Abstract

This paper presents MSMF (Multi-Scale Multi-Modal Fusion), a novel approach for enhanced stock market prediction. MSMF addresses key challenges in multi-modal stock analysis by integrating a modality completion encoder, multi-scale feature extraction, and an innovative fusion mechanism. Our model leverages blank learning and progressive fusion to balance complementarity and redundancy across modalities, while multi-scale alignment facilitates direct correlations between heterogeneous data types. We introduce Multi-Granularity Gates and a specialized architecture to optimize the integration of local and global information for different tasks. Additionally, a Task-targeted Prediction layer is employed to preserve both coarse and fine-grained features during fusion. Experimental results demonstrate that MSMF outperforms existing methods, achieving significant improvements in accuracy and reducing prediction errors across various stock market forecasting tasks. This research contributes valuable insights to the field of multi-modal financial analysis and offers a robust framework for enhanced market prediction.