IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0325459.html
   My bibliography  Save this article

Biased echoes: Large language models reinforce investment biases and increase portfolio risks of private investors

Author

Listed:
  • Philipp Winder
  • Christian Hildebrand
  • Jochen Hartmann

Abstract

Large language models are increasingly used by private investors seeking financial advice. The current paper examines the potential of these models to perpetuate investment biases and affect the economic security of individuals at scale. We provide a systematic assessment of how large language models used for investment advice shape the portfolio risks of private investors. We offer a comprehensive model of large language model investment advice risk, examining five key dimensions of portfolio risks (geographical cluster risk, sector cluster risk, trend chasing risk, active investment allocation risk, and total expense risk). We demonstrate across four studies that large language models used for investment advice induce increased portfolio risks across all five risk dimensions, and that a range of debiasing interventions only partially mitigate these risks. Our findings show that large language models exhibit similar “cognitive” biases as human investors, reinforcing existing investment biases inherent in their training data. These findings have important implications for private investors, policymakers, artificial intelligence developers, financial institutions, and the responsible development of large language models in the financial sector.

Suggested Citation

  • Philipp Winder & Christian Hildebrand & Jochen Hartmann, 2025. "Biased echoes: Large language models reinforce investment biases and increase portfolio risks of private investors," PLOS ONE, Public Library of Science, vol. 20(6), pages 1-24, June.
  • Handle: RePEc:plo:pone00:0325459
    DOI: 10.1371/journal.pone.0325459
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0325459
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0325459&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0325459?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Felix Holzmeister & Martin Holmén & Michael Kirchler & Matthias Stefan & Erik Wengström, 2023. "Delegation Decisions in Finance," Management Science, INFORMS, vol. 69(8), pages 4828-4844, August.
    2. Ana Valenzuela & Stefano Puntoni & Donna Hoffman & Noah Castelo & Julian De Freitas & Berkeley Dietvorst & Christian Hildebrand & Young Eun Huh & Robert Meyer & Miriam E. Sweeney & Sanaz Talaifar & Ge, 2024. "How Artificial Intelligence Constrains the Human Experience," Journal of the Association for Consumer Research, University of Chicago Press, vol. 9(3), pages 241-256.
    3. Agostino Capponi & Sveinn Ólafsson & Thaleia Zariphopoulou, 2022. "Personalized Robo-Advising: Enhancing Investment Through Client Interaction," Management Science, INFORMS, vol. 68(4), pages 2485-2512, April.
    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. Yongping Bao & Ludwig Danwitz & Fabian Dvorak & Sebastian Fehrler & Lars Hornuf & Hsuan Yu Lin & Bettina von Helversen, 2022. "Similarity and Consistency in Algorithm-Guided Exploration," CESifo Working Paper Series 10188, CESifo.
    2. Scherer, Bernd & Lehner, Sebastian, 2025. "What drives robo-advice?," Journal of Empirical Finance, Elsevier, vol. 80(C).
    3. Wolfgang Breuer & Andreas Knetsch, 2023. "Recent trends in the digitalization of finance and accounting," Journal of Business Economics, Springer, vol. 93(9), pages 1451-1461, November.
    4. Eriksen, Kristoffer W. & Kvaløy, Ola & Luzuriaga, Miguel, 2020. "Risk-taking on behalf of others," Journal of Behavioral and Experimental Finance, Elsevier, vol. 26(C).
    5. Haoyang Cao & Zhengqi Wu & Renyuan Xu, 2024. "Inference of Utilities and Time Preference in Sequential Decision-Making," Papers 2405.15975, arXiv.org, revised Jun 2024.
    6. Ng, Kenneth Tsz Hin & Chong, Wing Fung, 2024. "Optimal investment in defined contribution pension schemes with forward utility preferences," Insurance: Mathematics and Economics, Elsevier, vol. 114(C), pages 192-211.
    7. Oehler, Andreas & Horn, Matthias, 2024. "Does ChatGPT provide better advice than robo-advisors?," Finance Research Letters, Elsevier, vol. 60(C).
    8. repec:osf:osfxxx:dnjgz_v1 is not listed on IDEAS
    9. Nobuyuki Hanaki & Bolin Mao & Tiffany Tsz Kwan Tse & Wenxin Zhou, 2024. "Valuing Algorithms Over Experts: Evidence from a Stock Price Forecasting Experiment," ISER Discussion Paper 1268, Institute of Social and Economic Research, The University of Osaka.
    10. Hu, Xiao & Kang, Siqin & Ren, Long & Zhu, Shaokeng, 2024. "Interactive preference analysis: A reinforcement learning framework," European Journal of Operational Research, Elsevier, vol. 319(3), pages 983-998.
    11. Huber, Christoph & König-Kersting, Christian & Marini, Matteo M., 2025. "Experimenting with financial professionals," Journal of Banking & Finance, Elsevier, vol. 170(C).
    12. Kling, Luisa & König-Kersting, Christian & Trautmann, Stefan T., 2019. "Investment Preferences and Risk Perception: Financial Agents versus Clients," Working Papers 0674, University of Heidelberg, Department of Economics.
    13. Kling, Luisa & König-Kersting, Christian & Trautmann, Stefan T., 2023. "Investment preferences and risk perception: Financial agents versus clients," Journal of Banking & Finance, Elsevier, vol. 154(C).
    14. Rita Gonçalves, Ana & Costa Pinto, Diego & Gonzalez-Jimenez, Héctor & Dalmoro, Marlon & Mattila, Anna S., 2025. "Me, Myself, and My AI: How artificial intelligence classification failures threaten consumers’ self-expression," Journal of Business Research, Elsevier, vol. 186(C).
    15. Kaawach, Said & Kowalewski, Oskar & Talavera, Oleksandr, 2024. "Automatic versus manual investing: Role of past performance," Journal of Financial Stability, Elsevier, vol. 74(C).
    16. Köbis, Nils & Rahwan, Zoe & Bersch, Clara & Ajaj, Tamer & Bonnefon, Jean-François & Rahwan, Iyad, 2024. "Experimental evidence that delegating to intelligent machines can increase dishonest behaviour," OSF Preprints dnjgz, Center for Open Science.
    17. Martin Holmén & Felix Holzmeister & Michael Kirchler & Matthias Stefan & Erik Wengström, 2023. "Economic Preferences and Personality Traits Among Finance Professionals and the General Population," The Economic Journal, Royal Economic Society, vol. 133(656), pages 2949-2977.
    18. van Dolder, Dennie & Vandenbroucke, Jurgen, 2024. "Behavioral risk profiling: Measuring loss aversion of individual investors," Journal of Banking & Finance, Elsevier, vol. 168(C).
    19. Matthias Stefan & Martin Holmén & Felix Holzmeister & Michael Kirchler & Erik Wengström, 2022. "You can’t always get what you want—An experiment on finance professionals' decisions for others," Working Papers 2022-02, Faculty of Economics and Statistics, Universität Innsbruck.
    20. Keffert, Henk, 2024. "Robo-advising: Optimal investment with mismeasured and unstable risk preferences," European Journal of Operational Research, Elsevier, vol. 315(1), pages 378-392.
    21. Back, Camila & Morana, Stefan & Spann, Martin, 2023. "When do robo-advisors make us better investors? The impact of social design elements on investor behavior," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 103(C).

    More about this item

    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:plo:pone00:0325459. 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: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    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.