설명 가능한 GPT 주식투자분석 시스템 연구: RAG 구조와 멀티 AI 에이전트 통합 설계

This study implemented an automated stock investment analysis system combining ChatGPT-4o, role-based multi-AI (Artificial Intelligence) agents, and a RAG (Retrieval-Augmented Generation) framework. It aims to collect and analyze financial/non-financial data, news sentiment, industry competitiveness, and ESG (Environmental, Social, and Governance) information in real time, producing interpretable investment reports. The system integrates with DART(Data Analysis, Retrieval and Transfer System) similar to the U.S. SEC(Securities and Exchange Commission), Bank of Korea ECOS(Economic Statistics System), and Google News & Finance API (Application Programming Interface) for automated data retrieval. Eleven AI agents perform planning, analysis, prediction, and integrated judgment. Machine learning models are combined with LLM-based explanations to overcome black-box interpretability limits. Results show the system automates the entire process from planning to final report generation, and the integrated analysis is applicable to investment decision-making. This research offers a real-time, explainable, automated framework for financial AI, with potential uses in investment advisory, robo-advisors, and corporate IR (Investor Relations) support.