IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2401.07345.html
   My bibliography  Save this paper

Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice

Author

Listed:
  • Jeongbin Kim
  • Matthew Kovach
  • Kyu-Min Lee
  • Euncheol Shin
  • Hector Tzavellas

Abstract

This paper explores the use of Large Language Models (LLMs) as decision aids, with a focus on their ability to learn preferences and provide personalized recommendations. To establish a baseline, we replicate standard economic experiments on choice under risk (Choi et al., 2007) with GPT, one of the most prominent LLMs, prompted to respond as (i) a human decision maker or (ii) a recommendation system for customers. With these baselines established, GPT is provided with a sample set of choices and prompted to make recommendations based on the provided data. From the data generated by GPT, we identify its (revealed) preferences and explore its ability to learn from data. Our analysis yields three results. First, GPT's choices are consistent with (expected) utility maximization theory. Second, GPT can align its recommendations with people's risk aversion, by recommending less risky portfolios to more risk-averse decision makers, highlighting GPT's potential as a personalized decision aid. Third, however, GPT demonstrates limited alignment when it comes to disappointment aversion.

Suggested Citation

  • Jeongbin Kim & Matthew Kovach & Kyu-Min Lee & Euncheol Shin & Hector Tzavellas, 2024. "Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice," Papers 2401.07345, arXiv.org.
  • Handle: RePEc:arx:papers:2401.07345
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2401.07345
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Pawe{l} Niszczota & Sami Abbas, 2023. "GPT has become financially literate: Insights from financial literacy tests of GPT and a preliminary test of how people use it as a source of advice," Papers 2309.00649, arXiv.org.
    2. Chambers,Christopher P. & Echenique,Federico, 2016. "Revealed Preference Theory," Cambridge Books, Cambridge University Press, number 9781107087804.
    3. Alejandro Lopez-Lira & Yuehua Tang, 2023. "Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models," Papers 2304.07619, arXiv.org, revised Sep 2023.
    4. Echenique, Federico & Imai, Taisuke & Saito, Kota, 2023. "Approximate Expected Utility Rationalization," Department of Economics, Working Paper Series qt8pt4287c, Department of Economics, Institute for Business and Economic Research, UC Berkeley.
    5. Taylor Webb & Keith J. Holyoak & Hongjing Lu, 2023. "Emergent analogical reasoning in large language models," Nature Human Behaviour, Nature, vol. 7(9), pages 1526-1541, September.
    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. Samson Alva & Battal Dou{g}an, 2021. "Choice and Market Design," Papers 2110.15446, arXiv.org, revised Nov 2021.
    2. Christopher P. Chambers & Federico Echenique & Eran Shmaya, 2014. "The Axiomatic Structure of Empirical Content," American Economic Review, American Economic Association, vol. 104(8), pages 2303-2319, August.
    3. Changkuk Im & John Rehbeck, 2021. "Non-rationalizable Individuals, Stochastic Rationalizability, and Sampling," Papers 2102.03436, arXiv.org, revised Oct 2021.
    4. Cherchye, Laurens & Demuynck, Thomas & De Rock, Bram, 2018. "Transitivity of preferences: when does it matter?," Theoretical Economics, Econometric Society, vol. 13(3), September.
    5. Pawel Dziewulski, 2016. "Eliciting the just-noticeable difference," Economics Series Working Papers 798, University of Oxford, Department of Economics.
    6. Simone Cerreia-Vioglio & David Dillenberger & Pietro Ortoleva & Gil Riella, 2019. "Deliberately Stochastic," American Economic Review, American Economic Association, vol. 109(7), pages 2425-2445, July.
      • Simone Cerreia-Vioglio & David Dillenberger & Pietro Ortoleva & Gil Riella, 2012. "Deliberately Stochastic," PIER Working Paper Archive 17-013, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, revised 25 May 2017.
    7. Federico Echenique & SangMok Lee & Matthew Shum & M. Bumin Yenmez, 2021. "Stability and Median Rationalizability for Aggregate Matchings," Games, MDPI, vol. 12(2), pages 1-15, April.
    8. Keigo Inukai & Yuta Shimodaira & Kohei Shiozawa, 2022. "Revisiting CES utility functions for distributional preferences: Do people face the equality–efficiency trade-off?," ISER Discussion Paper 1195, Institute of Social and Economic Research, Osaka University.
    9. Sylvain Chassang & Kei Kawai & Jun Nakabayashi & Juan Ortner, 2019. "Data Driven Regulation: Theory and Application to Missing Bids," Boston University - Department of Economics - Working Papers Series WP2019-04, Boston University - Department of Economics.
    10. Domenico Cantone & Alfio Giarlotta & Stephen Watson, 2021. "Choice resolutions," Social Choice and Welfare, Springer;The Society for Social Choice and Welfare, vol. 56(4), pages 713-753, May.
    11. Aluma Dembo & Shachar Kariv & Matthew Polisson & John Quah, 2021. "Ever since Allais," IFS Working Papers W21/15, Institute for Fiscal Studies.
    12. Echenique, Federico & Miyashita, Masaki & Nakamura, Yuta & Pomatto, Luciano & Vinson, Jamie, 2022. "Twofold multiprior preferences and failures of contingent reasoning," Journal of Economic Theory, Elsevier, vol. 202(C).
    13. Müller, Daniel, 2019. "The anatomy of distributional preferences with group identity," Journal of Economic Behavior & Organization, Elsevier, vol. 166(C), pages 785-807.
    14. Federico Echenique & Taisuke Imai & Kota Saito, 2018. "Approximate Expected Utility Rationalization," CESifo Working Paper Series 7348, CESifo.
    15. Liping Wang & Jiawei Li & Lifan Zhao & Zhizhuo Kou & Xiaohan Wang & Xinyi Zhu & Hao Wang & Yanyan Shen & Lei Chen, 2023. "Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey," Papers 2308.04947, arXiv.org.
    16. Alex Kim & Maximilian Muhn & Valeri Nikolaev, 2023. "From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI," Papers 2310.17721, arXiv.org.
    17. Henson, Andrew F. & Rogers, Abbie A. & Gibson, Fiona L. & Burton, Michael P., 2018. "Value of Grower Group Services to Western Australian Farmers: a Discrete Choice Experiment," Working Papers 270160, University of Western Australia, School of Agricultural and Resource Economics.
    18. H. Spencer Banzhaf & Yaqin Liu & Martin Smith & Frank Asche, 2019. "Non-Parametric Tests of the Tragedy of the Commons," NBER Working Papers 26398, National Bureau of Economic Research, Inc.
    19. Miguel A. Costa‐Gomes & Carlos Cueva & Georgios Gerasimou & Matúš Tejiščák, 2022. "Choice, deferral, and consistency," Quantitative Economics, Econometric Society, vol. 13(3), pages 1297-1318, July.
    20. Echenique, Federico & Imai, Taisuke & Saito, Kota, 2023. "Approximate Expected Utility Rationalization," Department of Economics, Working Paper Series qt8pt4287c, Department of Economics, Institute for Business and Economic Research, UC Berkeley.

    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:2401.07345. 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.