Application of Multimodal Financial Data Fusion Analysis in Corporate Strategic Management

Abstract In the era of big data, financial data has evolved into a complex, multimodal information system, comprising structured financial statements, textual reports, market trends, and even real-time alternative data sources. The ability to effectively integrate and analyze such diverse datasets is crucial for corporate strategic management. This study explores an advanced multimodal data fusion framework for financial analysis, leveraging natural language processing, deep learning, and knowledge graph techniques to integrate financial reports, numerical indicators, and external market signals. The proposed approach enhances decision-making processes by identifying hidden patterns, reducing information asymmetry, and improving risk assessment accuracy. Experimental results on a benchmark corporate financial dataset demonstrate that multimodal data fusion significantly improves predictive performance in strategic decision-making compared to traditional single-source analyses. The study highlights the transformative potential of AI-driven multimodal financial analytics in optimizing corporate strategies, investment planning, and risk management.