IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2504.05862.html
   My bibliography  Save this paper

Are Generative AI Agents Effective Personalized Financial Advisors?

Author

Listed:
  • Takehiro Takayanagi
  • Kiyoshi Izumi
  • Javier Sanz-Cruzado
  • Richard McCreadie
  • Iadh Ounis

Abstract

Large language model-based agents are becoming increasingly popular as a low-cost mechanism to provide personalized, conversational advice, and have demonstrated impressive capabilities in relatively simple scenarios, such as movie recommendations. But how do these agents perform in complex high-stakes domains, where domain expertise is essential and mistakes carry substantial risk? This paper investigates the effectiveness of LLM-advisors in the finance domain, focusing on three distinct challenges: (1) eliciting user preferences when users themselves may be unsure of their needs, (2) providing personalized guidance for diverse investment preferences, and (3) leveraging advisor personality to build relationships and foster trust. Via a lab-based user study with 64 participants, we show that LLM-advisors often match human advisor performance when eliciting preferences, although they can struggle to resolve conflicting user needs. When providing personalized advice, the LLM was able to positively influence user behavior, but demonstrated clear failure modes. Our results show that accurate preference elicitation is key, otherwise, the LLM-advisor has little impact, or can even direct the investor toward unsuitable assets. More worryingly, users appear insensitive to the quality of advice being given, or worse these can have an inverse relationship. Indeed, users reported a preference for and increased satisfaction as well as emotional trust with LLMs adopting an extroverted persona, even though those agents provided worse advice.

Suggested Citation

  • Takehiro Takayanagi & Kiyoshi Izumi & Javier Sanz-Cruzado & Richard McCreadie & Iadh Ounis, 2025. "Are Generative AI Agents Effective Personalized Financial Advisors?," Papers 2504.05862, arXiv.org, revised Apr 2025.
  • Handle: RePEc:arx:papers:2504.05862
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2504.05862
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. David J. Streich, 2023. "Risk Preference Elicitation and Financial Advice Taking," Journal of Behavioral Finance, Taylor & Francis Journals, vol. 24(3), pages 259-275, July.
    2. Christian Hildebrand & Anouk Bergner, 2021. "Conversational robo advisors as surrogates of trust: onboarding experience, firm perception, and consumer financial decision making," Journal of the Academy of Marketing Science, Springer, vol. 49(4), pages 659-676, July.
    3. Tim Loughran & Bill Mcdonald, 2011. "When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10‐Ks," Journal of Finance, American Finance Association, vol. 66(1), pages 35-65, February.
    4. Charness, Gary & Gneezy, Uri & Imas, Alex, 2013. "Experimental methods: Eliciting risk preferences," Journal of Economic Behavior & Organization, Elsevier, vol. 87(C), pages 43-51.
    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. Gu, Chen & Kurov, Alexander & Wolfe, Marketa Halova, 2018. "Relief Rallies after FOMC Announcements as a Resolution of Uncertainty," Journal of Empirical Finance, Elsevier, vol. 49(C), pages 1-18.
    2. Peter John Robinson & W. J. Wouter Botzen & Fujin Zhou, 2021. "An experimental study of charity hazard: The effect of risky and ambiguous government compensation on flood insurance demand," Journal of Risk and Uncertainty, Springer, vol. 63(3), pages 275-318, December.
    3. Galliera, Arianna, 2018. "Self-selecting random or cumulative pay? A bargaining experiment," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 72(C), pages 106-120.
    4. Müller, Karsten, 2020. "German forecasters' narratives: How informative are German business cycle forecast reports?," Working Papers 23, German Research Foundation's Priority Programme 1859 "Experience and Expectation. Historical Foundations of Economic Behaviour", Humboldt University Berlin.
    5. Ranganathan, Kavitha & Lejarraga, Tomás, 2021. "Elicitation of risk preferences through satisficing," Journal of Behavioral and Experimental Finance, Elsevier, vol. 32(C).
    6. Aaryan Gupta & Vinya Dengre & Hamza Abubakar Kheruwala & Manan Shah, 2020. "Comprehensive review of text-mining applications in finance," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 6(1), pages 1-25, December.
    7. Yan Luo & Linying Zhou, 2020. "Textual tone in corporate financial disclosures: a survey of the literature," International Journal of Disclosure and Governance, Palgrave Macmillan, vol. 17(2), pages 101-110, September.
    8. Jiao Ji & Oleksandr Talavera & Shuxing Yin, 2018. "The Hidden Information Content: Evidence from the Tone of Independent Director Reports," Working Papers 2018-28, Swansea University, School of Management.
    9. Bennani, Hamza & Romelli, Davide, 2024. "Exploring the informativeness and drivers of tone during committee meetings: The case of the Federal Reserve," Journal of International Money and Finance, Elsevier, vol. 148(C).
    10. Goytom Abraha Kahsay & Daniel Osberghaus, 2018. "Storm Damage and Risk Preferences: Panel Evidence from Germany," Environmental & Resource Economics, Springer;European Association of Environmental and Resource Economists, vol. 71(1), pages 301-318, September.
    11. Banuri,Sheheryar & Murgia,Lucia Milena & Ul Haq,Imtiaz, 2023. "The Power of Religion: Islamic Investing in the Lab," Policy Research Working Paper Series 10459, The World Bank.
    12. Qian Wang & Duowen Wu & Lina Yan, 2021. "Effect of positive tone in MD&A disclosure on capital structure adjustment speed: evidence from China," Accounting and Finance, Accounting and Finance Association of Australia and New Zealand, vol. 61(4), pages 5809-5845, December.
    13. Bennani, Hamza, 2018. "Media coverage and ECB policy-making: Evidence from an augmented Taylor rule," Journal of Macroeconomics, Elsevier, vol. 57(C), pages 26-38.
    14. Umar, Tarik, 2022. "Complexity aversion when SeekingAlpha," Journal of Accounting and Economics, Elsevier, vol. 73(2).
    15. Dalton, Patricio S. & Nhung, Nguyen & Rüschenpöhler, Julius, 2020. "Worries of the poor: The impact of financial burden on the risk attitudes of micro-entrepreneurs," Journal of Economic Psychology, Elsevier, vol. 79(C).
    16. Hiroyuki Yamada & Yuki Kanayama & Kanako Yoshikawa & Kyaw Wai Aung, 2023. "Risk attitude, risky behaviour and price determination in the sex market: A case study of Yangon, Myanmar," Pacific Economic Review, Wiley Blackwell, vol. 28(5), pages 665-691, December.
    17. Belzil, Christian & Sidibé, Modibo, 2016. "Internal and External Validity of Experimental Risk and Time Preferences," IZA Discussion Papers 10348, Institute of Labor Economics (IZA).
    18. Alkaraan, Fadi & Elmarzouky, Mahmoud & Hussainey, Khaled & Venkatesh, V.G., 2023. "Sustainable strategic investment decision-making practices in UK companies: The influence of governance mechanisms on synergy between industry 4.0 and circular economy," Technological Forecasting and Social Change, Elsevier, vol. 187(C).
    19. Sophie Massin & Antoine Nebout & Bruno Ventelou, 2018. "Predicting medical practices using various risk attitude measures," The European Journal of Health Economics, Springer;Deutsche Gesellschaft für Gesundheitsökonomie (DGGÖ), vol. 19(6), pages 843-860, July.
    20. Pablo Brañas‐Garza & Matteo M. Galizzi & Jeroen Nieboer, 2018. "Experimental And Self‐Reported Measures Of Risk Taking And Digit Ratio (2d:4d): Evidence From A Large, Systematic Study," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 59(3), pages 1131-1157, August.

    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:2504.05862. 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.