Stock Investment Risk Analysis Using CrewAI Multi-Agent System
Keywords:
Artificial Intelligence (AI), CrewAI, Multi-agent systems, Personalized trading advice, Real-time data analysis, Risk analysis, Stock investmentAbstract
This paper describes the full implementation of an AI-driven platform for investment risk analysis that leverages the CrewAI multi-agent framework powered by Llama 3.2-3b. The platform integrates real-time financial data from sources such as NewsAPI and Alpha Vantage and processes this data through specialized AI agents deployed within a Django-based backend. The system produces actionable outputs including personalized risk assessments, cumulative returns, and trading signals. Experimental evaluation demonstrates enhanced predictive accuracy and responsiveness compared to traditional methods. This work builds upon our prior literature survey and related studies, underscoring the value of advanced multi-agent AI systems for dynamic financial decision-making.
References
D. Mai, "StockGPT: A GenAI Model for Stock Prediction and Trading," Arxiv Preprint, 2024.J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol. 2. Oxford: Clarendon, 1892, pp.68–73, https://doi.org/10.48550/arXiv.2404.05101
L. Li, T.-Y. Chang, and H. Wang, “Multimodal Gen-AI for Fundamental Investment Research,” Arxiv.Org, 2023. https://arxiv.org/abs/2401.06164
T. Sepanosian, Z. Milosevic, and A. Blair, “Scaling AI Adoption in Finance: Modelling Framework and Implementation Study,” Lecture Notes in Business Information Processing, pp. 221–236, 2025, doi: https://doi.org/10.1007/978-3-031-79059-1_14.
Han, N. Wang, S. Che, H. Yang, K. Zhang, and S. X. Xu, “Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research,” In 5th ACM International Conference on AI in Finance (ICAIF '24), Brooklyn, NY, USA, Nov. 2024. https://ideas.repec.org/p/arx/papers/2411.04788.html
A. Borkowski and A. Ben-Ari, “Muli-Agent AI Systems in Healthcare: Technical and Clinical Analysis,” Preprints, Oct. 2024, doi: https://doi.org/10.20944/preprints202410.0182.v1.
X. Wang, Y. Wang, B. Weng, and A. Vinel, “Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network,” Arxiv, Sept. 29, 2020. https://arxiv.org/abs/2010.01197
Z. Shi, Y. Hu, G. Mo, and J. Wu, “Attention‑based CNN‑LSTM and XGBoost Hybrid Model for Stock Prediction,” Arxiv, Apr. 6, 2022. https://arxiv.org/abs/2204.02623
S. Gehrmann., C. Huan, X. Teng, “Understanding and Mitigating Risks of Generative AI in Financial Services,” Arxiv.Org, 2025, doi: https://doi.org/10.1145/3715275.3732168.
S. Mestiri, “Machine Learning Techniques in Financial Applications,” Journal of Research, Innovation and Technologies (JoRIT), vol. 3, no. 16, p. 30, Mar. 2024, doi: https://doi.org/10.57017/jorit.v3.1(5).02.
N. Rane, S. Choudhary, and J. Rane, “Blockchain and Artificial Intelligence (AI) integration for revolutionizing security and transparency in finance,” Social Science Research Network, Dec. 2023, doi: https://doi.org/10.2139/ssrn.4644253.
N. Lutimath, K. Bhuvanesh, and M. Zidan, “The Design of Hand Gesture Controlled Virtual Mouse Using Convolutional Neural Network Technique. International Journal of Innovative Research in Technology, vol. 9, no. 10, 2023, Jun. 26. Available: https://ijirt.org/publishedpaper/ijirt159999_paper.pdf
M. D.R, S. Kumar S, Sai, and L. J.J, “Enhancing Personalized Learning based on AI-Driven Lesson Plan Generator Using Mistral-7B for Efficient Content Extraction and Summarization,” Zenodo, Jun. 2024, doi: https://doi.org/10.5281/zenodo.12578736.
A. S. Naik, E. Yeniaras, G. Hellstern, G. Prasad, and S. Kumar, “From portfolio optimization to quantum blockchain and security: a systematic review of quantum computing in finance,” Financial Innovation, vol. 11, no. 1, Feb. 2025, doi: https://doi.org/10.1186/s40854-025-00751-6.
A. Alenizi, S. Mishra, and A. Baihan, “Enhancing secure financial transactions through the synergy of blockchain and artificial intelligence,” Ain Shams Engineering Journal/Ain Shams Engineering Journal, pp. 102733–102733, Mar. 2024, doi: https://doi.org/10.1016/j.asej.2024.102733.
D. Herman , C. Googin, X. Liu, “A Survey of Quantum Computing for Finance,” Arxiv:2201.02773, Jan. 2022, Available: https://arxiv.org/abs/2201.02773
J. Zhou, “Quantum Finance: Exploring the Implications of Quantum Computing on Financial Models,” Computational Economics, 2025, doi: https://doi.org/10.1007/s10614 025 10894 4.
D. B. Vuković, S. Dekpo Adza, and S. Matović, “AI integration in financial services: a systematic review of trends and regulatory challenges,” Humanities and Social Sciences Communications, vol. 12, art. 562, 2025, doi: https://doi.org/10.1057/s41599-025-04850-8.
S. Merikapudi, S. Math, C. Nandini, and M. Rafi, “A GoogleNet assisted CNN architecture combined with feature attention blocks and Gaussian distribution for video face recognition and verification,” Int. J. Electr. Eng. Technol. (IJEET), vol. 12, no. 1, pp. 30–42, Jan. 2021, Art. no. IJEET_12_01_004. https://iaeme.com/Home/article_id/IJEET_12_01_004
M. D. H. R., S. S., A. Kumar Gupta, and K. Mayee Adavala, “View of Evolutionary Strategies for Parameter Optimization in Deep Learning Models,” Ijisae.org, 2025. https://ijisae.org/index.php/IJISAE/article/view/3636/2252.
