Knowledge Graph Construction for Stock Markets with LLM-Based Explainable Reasoning

TL;DR

This paper addresses the need for relational, explainable analysis in stock markets beyond pure time-series prediction. It introduces a stock-market knowledge graph and an LLM-based reasoning layer that performs multi-hop queries and generates explainable answers. The main contributions are the construction of a comprehensive GraphDB for Korean market data, the integration of LLMs with graph-based reasoning for finance, and practical case studies demonstrating insights unattainable with traditional queries. The approach offers a scalable tool for investors and analysts to uncover interdependencies among companies, indicators, and sectors.

Abstract

The stock market is inherently complex, with interdependent relationships among companies, sectors, and financial indicators. Traditional research has largely focused on time-series forecasting and single-company analysis, relying on numerical data for stock price prediction. While such approaches can provide short-term insights, they are limited in capturing relational patterns, competitive dynamics, and explainable investment reasoning. To address these limitations, we propose a knowledge graph schema specifically designed for the stock market, modeling companies, sectors, stock indicators, financial statements, and inter-company relationships. By integrating this schema with large language models (LLMs), our approach enables multi-hop reasoning and relational queries, producing explainable and in-depth answers to complex financial questions. Figure1 illustrates the system pipeline, detailing the flow from data collection and graph construction to LLM-based query processing and answer generation. We validate the proposed framework through practical case studies on Korean listed companies, demonstrating its capability to extract insights that are difficult or impossible to obtain from traditional database queries alone. The results highlight the potential of combining knowledge graphs with LLMs for advanced investment analysis and decision support.

Figures (3)

• Figure 1: A pipeline for GraphDB construction and LLM-based inference system
• Figure 2: An example of the graph database
• Figure 3: An overview of the proposed graph schema