Implementation of a multi-agent artificial intelligence system for financial trading decision-making process
DOI:
https://doi.org/10.15291/oec.4863Keywords:
multi-agent systems, artificial intelligence, natural language processing, trading strategies, risk managementAbstract
The application of artificial intelligence in financial analysis leads to the development of advanced multi-agent systems that enable more effective analysis and decision-making than existing methods. This paper presents the development and implementation of a multi-agent artificial intelligence system for generating financial trading recommendations, integrating specialized agents for data collection, technical analysis, news processing, and portfolio management. The system combines quantitative analysis based on technical indicators with qualitative insights from financial news, utilizing natural language processing techniques such as prompt engineering and retrieval-augmented generation. The system's architecture enables autonomous operation of four specialized agents that contribute to generating trading recommendations. An evaluation conducted over six months in 2025 on five representative technology stocks reveals a significant improvement in risk management compared to the "buy and hold" reference strategy. Results demonstrate a significant reduction in volatility and maximum drawdown for most analysed stocks, particularly for highly volatile stocks such as Tesla, where the system maintains a maximum drawdown of 7.72% compared to 47.84% for the reference strategy. The system adapts trading recommendations to various market conditions and the specifics of each stock, thereby maintaining portfolio stability during periods of market instability. Financial news analysis using NLP enables the system to recognize whether news is positive or negative, its importance to the stock, and how it may affect its price. Despite identified limitations in adopting a more cautious approach during strong upward trends, the modularity of this architecture enables the continuous development and optimization of individual components. The research confirms the value of multi-agent approaches in integrating different data sources to improve the trading decision-making process.
References
Acharya, D. B., Kuppan, K. and Divya, B. (2025). Agentic AI: Autonomous Intelligence for Complex Goals - A Comprehensive Survey. IEEE Access.
Aldhyani, T. H. H. and Alzahrani, A. (2022). Framework for Predicting and Modeling Stock Market Prices Based on Deep Learning Algorithms. Electronics (Switzerland), 11 (19)
Baek, Y. and Kim, H. Y. (2018). ModAugNet: A new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module. Expert Systems with Applications, 113, pp.457–480
Bartram, S. M. and Grinblatt, M. (2014). Fundamental Analysis Works
Botunac, I., Panjkota, A. and Matetic, M. (2020). The effect of feature selection on the performance of long short-term memory neural network in stock market predictions. In: Annals of DAAAM and Proceedings of the International DAAAM Symposium. 31 (1). 2020. DAAAM International Vienna. pp.592–598
Brown, T. B. et al. (2020). Language Models are Few-Shot Learners.
Callanan, E. et al. (2023). Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
Chen, B. et al. (2023). Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review.
Colby, R. W. (2003). The encyclopedia of technical market indicators. McGraw-Hill.
Fabozzi, F. J. et al. (2019). Foundations of global financial markets and institutions.
Fama, E. F. (1965). The behavior of stock-market prices.
Fama, E. F. (1970). Efficient Capital Markets A Review of Theory and Empirical Work.
Fama, E. F. (1991). Efficient Capital Markets: II. THE JOURNAL OF FINANCE *, XLVI (5).
Fischer, T. and Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270 (2), pp.654–669.
Gao, Y. et al. (2024). Retrieval-Augmented Generation for Large Language Models: A Survey.
Guida, T. (2018). Big Data and Machine Learning in Quantitative Investment
Han, X. et al. (2024). Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research.
Huang, A. H., Wang, H. and Yang, Y. (2023). FinBERT: A Large Language Model for Extracting Information from Financial Text*. Contemporary Accounting Research, 40 (2), pp.806–841.
Ku, C. S. et al. (2023). Improving Stock Market Predictions: An Equity Forecasting Scanner Using Long Short-Term Memory Method with Dynamic Indicators for Malaysia Stock Market. Mathematics, 11 (11).
Lewis, P. et al. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.
Liu, X.-Y. et al. (2023). Dynamic Datasets and Market Environments for Financial Reinforcement Learning
Mishkin, F. S. and Eakins, S. (2018). Financial Markets and Institutions.
Mosbach, M. et al. (2023). Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation.
Murphy, J. J. (1999). Technical analysis of the financial markets.
Olorunnimbe, K. and Viktor, H. (2023). Deep learning in the stock market—a systematic survey of practice, backtesting, and applications. Artificial Intelligence Review, 56 (3), pp.2057–2109.
Orsag, S. (2015). Investicijska analiza.
Saunders, A., Cornett, M. M. and Erhemjamts, O. (2022). Financial Markets and Institutions.
Tran, K.-T. et al. (2025). Multi-Agent Collaboration Mechanisms: A Survey of LLMs.
Wu, S. et al. (2023). BloombergGPT: A Large Language Model for Finance.
Yang, H., Liu, X.-Y. and Wang, C. D. (2023). FinGPT: Open-Source Financial Large Language Models.
Ye, A. et al. (2024). Learning the Market: Sentiment-Based Ensemble Trading Agents.
York, E. (2025). Trump tariffs: The economic impact of the trump trade war. [Online]. Available at: https://policycommons.net/artifacts/18122739/trump-tariffs/19022252/ [Pristupljeno 30.8.2025].
Zhang, C. et al. (2024a). When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments. In: 2022-March. 2024. p.47. [Online]
Zhang, W. et al. (2024b). A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 24 August 2024. Association for Computing Machinery. pp.4314–4325
Zou, J. et al. (2022). Stock Market Prediction via Deep Learning Techniques: A Survey.
