Downloads

https://doi.org/10.62836/iaet.v3i1.362
Kaixian Xu, Zhaoyan Zhang, Alan Wilson, & Yu Qiao. (2024). Generalizable Multi-Agent Framework for Quantitative Trading of US Education Funds. Innovations in Applied Engineering and Technology, 3(1), 1–12. https://doi.org/10.62836/iaet.v3i1.362
Volume 3, Issue 1, 2024

Generalizable Multi-Agent Framework for Quantitative Trading of US Education Funds

Quantitative trading of specialized financial instruments like US education funds  requires comprehensive analysis of both market dynamics and external influenc- ing factors.  This paper proposes a novel multi-agent framework that integrates  collaborative agents for market analysis, macroeconomic trend assessment, and  policy change evaluation, along with a multi-level reflection mechanism for contin- uous strategy optimization. Through extensive experiments using a comprehensive  dataset from 2018 to 2024, the framework demonstrates superior performance  compared to traditional rule-based strategies and machine learning approaches, achieving higher returns, better risk-adjusted performance, and enhanced risk man- agement capabilities.  The integration of multi-agent collaboration, non-market  factor analysis, and adaptive strategy refinement provides a robust solution for  achieving long-term investment goals in dynamic market environments.

multi-agent framework; quantitative trading; non-market factor analysis; multi-level reflection mechanism; US education funds

References

  1. Xie Q, Han W, Zhang X, et al. Pixiu: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance. arXiv 2023; arXiv:2306.05443.
  2. Yang H, Liu X-Y, Wang CD. Fingpt: Open-Source Financial Large Language Models. arXiv 2023; arXiv:2306.06031.
  3. Gan Y, Zhu D. The Research on Intelligent News Advertisement Recommendation Algorithm Based on Prompt Learning in End-to-End Large Language Model Architecture. Innovations in Applied Engineering and Technology 2024; 3(1): 1–19.
  4. Zhang B, Yang H, Liu X-Y. Instruct-Fingpt: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models. arXiv 2023; arXiv:2306.12659.
  5. Zhang S, Roller S, Goyal N, et al. Opt: Open Pre-Trained Transformer Language Models. arXiv 2022; arXiv:2205.01068.
  6. Wu S, Irsoy O, Lu S, et al. Bloomberggpt: A Large Language Model for Finance. arXiv 2023; arXiv:2303.17564.
  7. Zhang X, Yang Q, Xu D. Xuanyuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters. arXiv 2023; arXiv:2305.12002.
  8. Lu D, Wu H, Liang J, et al. Bbt-fin: Comprehensive Construction of Chinese Financial Domain Pre-Trained Language Model, Corpus and Benchmark. arXiv 2023; arXiv:2302.09432.
  9. Lopez-Lira A, Tang Y. Can chatgpt forecast stock price movements? Return Predictability and Large Language Models arXiv 2023; arXiv:2304.07619.
  10. Gan Y, Ma J, Xu K. Enhanced E-Commerce Sales Forecasting Using EEMD-Integrated LSTM Deep Learning Model. Journal of Computational Methods in Engineering Applications 2023; 3(1): 1–11.
  11. Gan Y, Chen X. The Research on End-to-End Stock Recommendation Algorithm Based on Time-Frequency Consistency. Advances in Computer and Communication 2024; 5(4).
  12. Fatouros G, Metaxas K, Soldatos J, et al. Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection. arXiv 2024; arXiv:2401.03737.
  13. Wang M, Izumi K, Sakaji H. LLMfactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction. arXiv 2024; arXiv:2406.10811.
  14. Ma J, Zhang Z, Xu K, et al. Improving the Applicability of Social Media Toxic Comments Prediction across Diverse Data Platforms Using Residual Self-Attention-Based LSTM Combined with Transfer Learning. Optimizations in Applied Machine Learning 2022; 2(1).
  15. Zhang H, Xu K, Gan Y, et al. Deep Reinforcement Learning Stock Trading Strategy Optimization Framework Based on Timesnet and Self-Attention Mechanism. Optimizations in Applied Machine Learning 2025; 5(1).
  16. Zhang W, Zhao L, Xia H, et al. A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist. arXiv 2024; arXiv:2402.18485.
  17. Xing F. Designing Heterogeneous LLM Agents for Financial Sentiment Analysis. arXiv 2024; arXiv:2401.05799.
  18. Ma J, Xu K, Qiao Y, et al. An Integrated Model for Social Media Toxic Comments Detection: Fusion of High-Dimensional Neural Network Representations and Multiple Traditional Machine Learning Algorithms. Journal of Computational Methods in Engineering Applications 2022; 2(1): 1–12.
  19. Li Y, Yu Y, Li H, et al. Tradinggpt: Multi-Agent System with Layered Memory and Distinct Characters for Enhanced Financial Trading Performance. arXiv 2023; arXiv:2309.03736.
  20. Koa KJ, Ma Y, Ng R, et al. Learning to Generate Explainable Stock Predictions Using Self-Reflective Large Language Models. In Proceedings of the ACM Web Conference, Singapore, 13–17 May 2024. http://dx.doi.org/10.1145/3589334.3645611.
  21. Ding Y, Jia S, Ma T, et al. Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction. arXiv 2023; arXiv:2310.05627.
  22. Schulman J, Wolski F, Dhariwal P, et al. Proximal Policy Optimization Algorithms. arXiv 2017; arXiv:1707.06347.
  23. Zhang Z. Rag for Personalized Medicine: A Framework for Integrating Patient Data and Pharmaceutical Knowledge for Treatment Recommendations. Optimizations in Applied Machine Learning 2024; 4(1).
  24. Yu Y, Li H, Chen Z, et al. Finmem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design. arXiv 2023; arXiv:2311.13743.
  25. Wang S, Yuan H, Zhou L, et al. Alpha-gpt: Human-AI Interactive Alpha Mining for Quantitative Investment. arXiv 2023; arXiv:2308.00016.
  26. Xu K, Gan Y, Wilson A. Stacked Generalization for Robust Prediction of Trust and Private Equity on Financial Performances. Innovations in Applied Engineering and Technology 2024; 3(1): 1–12.

Supporting Agencies

  1. Funding: Funding This research was supported by the U.S. National Science Foundation under Grant No. 2339596.