IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2411.04788.html
   My bibliography  Save this paper

Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research

Author

Listed:
  • Xuewen Han
  • Neng Wang
  • Shangkun Che
  • Hongyang Yang
  • Kunpeng Zhang
  • Sean Xin Xu

Abstract

In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI agents. In this paper, we propose a novel multi-agent collaboration system designed to enhance decision-making in financial investment research. The system incorporates agent groups with both configurable group sizes and collaboration structures to leverage the strengths of each agent group type. By utilizing a sub-optimal combination strategy, the system dynamically adapts to varying market conditions and investment scenarios, optimizing performance across different tasks. We focus on three sub-tasks: fundamentals, market sentiment, and risk analysis, by analyzing the 2023 SEC 10-K forms of 30 companies listed on the Dow Jones Index. Our findings reveal significant performance variations based on the configurations of AI agents for different tasks. The results demonstrate that our multi-agent collaboration system outperforms traditional single-agent models, offering improved accuracy, efficiency, and adaptability in complex financial environments. This study highlights the potential of multi-agent systems in transforming financial analysis and investment decision-making by integrating diverse analytical perspectives.

Suggested Citation

  • Xuewen Han & Neng Wang & Shangkun Che & Hongyang Yang & Kunpeng Zhang & Sean Xin Xu, 2024. "Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research," Papers 2411.04788, arXiv.org.
    • Handle: RePEc:arx:papers:2411.04788
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2411.04788
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yonca Ertimur & Jayanthi Sunder & Shyam V. Sunder, 2007. "Measure for Measure: The Relation between Forecast Accuracy and Recommendation Profitability of Analysts," Journal of Accounting Research, Wiley Blackwell, vol. 45(3), pages 567-606, June.
    2. Ko, Hyungjin & Lee, Jaewook, 2024. "Can ChatGPT improve investment decisions? From a portfolio management perspective," Finance Research Letters, Elsevier, vol. 64(C).
    3. Abarbanell, JS & Bushee, BJ, 1997. "Fundamental analysis, future earnings, and stock prices," Journal of Accounting Research, Wiley Blackwell, vol. 35(1), pages 1-24.
    4. Yuqi Nie & Yaxuan Kong & Xiaowen Dong & John M. Mulvey & H. Vincent Poor & Qingsong Wen & Stefan Zohren, 2024. "A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges," Papers 2406.11903, arXiv.org.
    5. Alex Kim & Maximilian Muhn & Valeri Nikolaev, 2024. "Financial Statement Analysis with Large Language Models," Papers 2407.17866, arXiv.org, revised Nov 2024.
    6. Yi Yang & Yixuan Tang & Kar Yan Tam, 2023. "InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning," Papers 2309.13064, arXiv.org.
    7. Hull, J.C., 2014. "The Evaluation of Risk in Business Investment," Elsevier Monographs, Elsevier, edition 1, number 9780080240749.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Tianyu Zhou & Pinqiao Wang & Yilin Wu & Hongyang Yang, 2024. "FinRobot: AI Agent for Equity Research and Valuation with Large Language Models," Papers 2411.08804, arXiv.org.
    2. Yuqi Nie & Yaxuan Kong & Xiaowen Dong & John M. Mulvey & H. Vincent Poor & Qingsong Wen & Stefan Zohren, 2024. "A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges," Papers 2406.11903, arXiv.org.
    3. Yuzhe Yang & Yifei Zhang & Yan Hu & Yilin Guo & Ruoli Gan & Yueru He & Mingcong Lei & Xiao Zhang & Haining Wang & Qianqian Xie & Jimin Huang & Honghai Yu & Benyou Wang, 2024. "UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models," Papers 2410.14059, arXiv.org, revised Oct 2024.
    4. Bradley Blaylock & Bradley P. Lawson & Michael A. Mayberry, 2020. "Taxable income, future profitability, and stock returns," Journal of Business Finance & Accounting, Wiley Blackwell, vol. 47(7-8), pages 858-881, July.
    5. Stephen A. Hillegeist & James P. Kavourakis & Matthew Pinnuck, 2023. "The association between quarter length, forecast errors, and firms’ voluntary disclosures," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 63(2), pages 1885-1918, June.
    6. Jessie Sun, 2019. "A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models," Papers 1905.04842, arXiv.org.
    7. Ghada A. Altarawneh & Ahmad B. Hassanat & Ahmad S. Tarawneh & Ahmad Abadleh & Malek Alrashidi & Mansoor Alghamdi, 2022. "Stock Price Forecasting for Jordan Insurance Companies Amid the COVID-19 Pandemic Utilizing Off-the-Shelf Technical Analysis Methods," Economies, MDPI, vol. 10(2), pages 1-18, February.
    8. Mauri, Alfredo J. & Lin, Jing & Neiva De Figueiredo, João, 2013. "The influence of strategic patterns of internationalization on the accuracy and bias of earnings forecasts by financial analysts," International Business Review, Elsevier, vol. 22(4), pages 725-735.
    9. Gikas Hardouvelis & George Papanastasopoulos & Dimitrios D. Thomakos & Tao Wang, 2007. "Accruals, Net Stock Issues and Value-Glamour Anomalies: New Evidence on their Relation," Working Paper series 47_07, Rimini Centre for Economic Analysis.
    10. Krolikowski, Marcin W. & Chen, Gaole & Mohr, Joseph E., 2016. "Optimism pattern of all-star analysts," International Review of Financial Analysis, Elsevier, vol. 47(C), pages 222-228.
    11. Daniel Arand & Alexander G. Kerl, 2015. "Sell†Side Analyst Research and Reported Conflicts of Interest," European Financial Management, European Financial Management Association, vol. 21(1), pages 20-51, January.
    12. Hirshleifer, David & Kewei Hou & Teoh, Siew Hong & Yinglei Zhang, 2004. "Do investors overvalue firms with bloated balance sheets?," Journal of Accounting and Economics, Elsevier, vol. 38(1), pages 297-331, December.
    13. Dafydd Mali & Hyoung‐joo Lim, 2021. "Do Relatively More Efficient Firms Demand Additional Audit Effort (Hours)?," Australian Accounting Review, CPA Australia, vol. 31(2), pages 108-127, June.
    14. Hoechle, Daniel & Schaub, nic & Schmid, Markus, 2012. "Time Stamp Errors and the Stock Price Reaction to Analyst Recommendation and Forecast Revisions," Working Papers on Finance 1215, University of St. Gallen, School of Finance, revised Sep 2015.
    15. Bartram, Söhnke M. & Grinblatt, Mark, 2018. "Agnostic fundamental analysis works," Journal of Financial Economics, Elsevier, vol. 128(1), pages 125-147.
    16. Ken Li, 2024. "Liquidity ratios and corporate failures," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 64(1), pages 1111-1134, March.
    17. Chi Chen & Li Zhao & Wei Cao & Jiang Bian & Chunxiao Xing, 2020. "Trimming the Sail: A Second-order Learning Paradigm for Stock Prediction," Papers 2002.06878, arXiv.org.
    18. Lu Zhang, 2017. "The Investment CAPM," European Financial Management, European Financial Management Association, vol. 23(4), pages 545-603, September.
    19. Chahine, Salim & Daher, Mai & Saade, Samer, 2021. "Doing good in periods of high uncertainty: Economic policy uncertainty, corporate social responsibility, and analyst forecast error," Journal of Financial Stability, Elsevier, vol. 56(C).
    20. Hess, Dieter & Kreutzmann, Daniel & Pucker, Oliver, 2011. "Projected earnings accuracy and the profitability of stock recommendations," CFR Working Papers 10-17 [rev.], University of Cologne, Centre for Financial Research (CFR).

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2411.04788. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.