Architecture and Evaluation of a Multi-Agent System for Market Monitoring
- 18 May 2026
- journal article
- Published by University Library in Kragujevac in Scientific Publications Of The State University Of Novi Pazar, series A: Applied Mathematics, Informatics and Mechanics
- Vol. 26 (1)
Abstract
The contemporary financial environment is characterized by a rapidly increasing volume of heterogeneous data, which necessitates automated solutions for their integration and analysis in the context of market dynamics. In this paper, a multi-agent system for automated monitoring and analysis of capital markets is presented, developed using the CrewAI framework and combining structured financial data with sentiment analysis of financial news. The proposed system integrates numerical data with textual content from relevant news sources, enabling the identification of information with a potential impact on stock price movements. The system architecture comprises two specialized agents: MarketScanner, responsible for analyzing market indicators and generating concise analytical reports, and NewsAggregator, which collects relevant news and performs sentiment analysis using large language models and the FinBERT model for financial text processing. The system was evaluated using data from Apple, Bank of America, and Exxon Mobil. Experimental results indicate that the integration of a multi-agent architecture with sentiment analysis supports systematic examination of market-relevant information. Sentiment classification accuracy reached above 80% in selected cases when evaluated against expert annotations. The findings suggest that sentiment–market relationships vary across companies and depend on the specific market context.Keywords
This publication has 11 references indexed in Scilit:
- Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deployment2025
- Predicting Stock Prices with FinBERT-LSTM: Integrating News Sentiment Analysis2024
- Stock Price Trend Prediction using Emotion Analysis of Financial Headlines with Distilled LLM Model2024
- Forecasting the S&P 500 Index Using Mathematical-Based Sentiment Analysis and Deep Learning Models: A FinBERT Transformer Model and LSTMAxioms, 2023
- FinBERT: A Large Language Model for Extracting Information from Financial Text*Contemporary Accounting Research, 2023
- Evaluation of Sentiment Analysis in Finance: From Lexicons to TransformersIEEE Access, 2020
- Enhanced news sentiment analysis using deep learning methodsJournal of Computational Social Science, 2019
- COUPLED NETWORK APPROACH TO PREDICTABILITY OF FINANCIAL MARKET RETURNS AND NEWS SENTIMENTSInternational Journal of Theoretical and Applied Finance, 2015
- News impact on stock price return via sentiment analysisKnowledge-Based Systems, 2014
- Cohesiveness in Financial News and its Relation to Market VolatilityScientific Reports, 2014