MULTI-AGENT FINANCIAL STATEMENT ANALYSIS SYSTEM

Financial statement analysis traditionally requires considerable manual effort to extract financial information, calculate ratios, assess risks, and prepare comprehensive reports. This paper presents a Multi-Agent Financial Statement Analysis System that automates these activities using Large Language Models, Retrieval-Augmented Generation, and specialized analytical agents. The system processes financial statement PDFs, extracts relevant information, stores document representations in a vector database, and retrieves contextual information for analysis. Dedicated agents perform financial metric extraction, ratio analysis, risk assessment, competitor analysis, SWOT analysis, and investment research report generation. The proposed approach provides a structured workflow for transforming financial documents into an integrated financial analysis.