IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2607.13670.html

Equilibrium Information Aggregation under Machine Learning

Author

Listed:
  • Andrew Ellis
  • Michele Piccione
  • Shengxing Zhang

Abstract

We introduce a framework for studying the equilibrium effects of machine learning. Agents process information using a Chow and Liu (1968) tree, a widely-used machine learning procedure that admits a closed-form solution. We apply the model to an asset market with dispersed information based on Hellwig (1980). The price mechanism fails to aggregate the information extracted by the algorithm, even approximately. While there are partial equilibrium benefits from access to algorithms, the equilibrium price aggregates less information than the rational equilibrium. Equilibrium typically features diverse world-models, demands, and utilities, even with ex ante identical agents.

Suggested Citation

  • Andrew Ellis & Michele Piccione & Shengxing Zhang, 2026. "Equilibrium Information Aggregation under Machine Learning," Papers 2607.13670, arXiv.org.
    • Handle: RePEc:arx:papers:2607.13670
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2607.13670
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Fudenberg, Drew & Romanyuk, Gleb & Strack, Philipp, 2017. "Active learning with a misspecified prior," Theoretical Economics, Econometric Society, vol. 12(3), September.
    2. Grossman, Sanford J, 1976. "On the Efficiency of Competitive Stock Markets Where Trades Have Diverse Information," Journal of Finance, American Finance Association, vol. 31(2), pages 573-585, May.
    3. Ignacio Esponda & Demian Pouzo, 2016. "Berk–Nash Equilibrium: A Framework for Modeling Agents With Misspecified Models," Econometrica, Econometric Society, vol. 84, pages 1093-1130, May.
    4. In-Koo Cho & Kenneth Kasa, 2015. "Learning and Model Validation," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 82(1), pages 45-82.
    5. Ran Spiegler, 2016. "Bayesian Networks and Boundedly Rational Expectations," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 131(3), pages 1243-1290.
    6. Bergemann, Dirk & Bonatti, Alessandro & Smolin, Alex, 2025. "Menu Pricing of Large Language Models," TSE Working Papers 25-1670, Toulouse School of Economics (TSE), revised Mar 2026.
    7. Kfir Eliaz & Ran Spiegler & Yair Weiss, 2021. "Cheating with Models," American Economic Review: Insights, American Economic Association, vol. 3(4), pages 417-434, December.
    8. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Misinterpreting Others and the Fragility of Social Learning," Econometrica, Econometric Society, vol. 88(6), pages 2281-2328, November.
    9. Grossman, Sanford J & Stiglitz, Joseph E, 1980. "On the Impossibility of Informationally Efficient Markets," American Economic Review, American Economic Association, vol. 70(3), pages 393-408, June.
    10. Dolgopolov, Arthur, 2024. "Reinforcement learning in a prisoner's dilemma," Games and Economic Behavior, Elsevier, vol. 144(C), pages 84-103.
    11. Albert S. Kyle, 1989. "Informed Speculation with Imperfect Competition," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 56(3), pages 317-355.
    12. Paul Heidhues & Botond Kőszegi & Philipp Strack, 2018. "Unrealistic Expectations and Misguided Learning," Econometrica, Econometric Society, vol. 86(4), pages 1159-1214, July.
    13. J. Aislinn Bohren & Daniel N. Hauser, 2021. "Learning With Heterogeneous Misspecified Models: Characterization and Robustness," Econometrica, Econometric Society, vol. 89(6), pages 3025-3077, November.
    14. Philippe Jehiel & Giacomo Weber, 2025. "Endogenous clustering and analogy-based expectation equilibrium," Papers 2505.13022, arXiv.org.
    15. Bohren, Aislinn & Hauser, Daniel, 2017. "Learning with Heterogeneous Misspecified Models: Characterization and Robustness," CEPR Discussion Papers 12036, Centre for Economic Policy Research.
    16. Admati, Anat R, 1985. "A Noisy Rational Expectations Equilibrium for Multi-asset Securities Markets," Econometrica, Econometric Society, vol. 53(3), pages 629-657, May.
    17. Cuimin Ba, 2026. "Robust Misspecified Models," American Economic Review, American Economic Association, vol. 116(4), pages 1340-1379, April.
    18. Hellwig, Martin F., 1980. "On the aggregation of information in competitive markets," Journal of Economic Theory, Elsevier, vol. 22(3), pages 477-498, June.
    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. Ignacio Esponda & Demian Pouzo, 2026. "Learning and Equilibrium under Model Misspecification," Papers 2601.09891, arXiv.org.
    2. He, Kevin & Libgober, Jonathan, 2025. "Misspecified learning and evolutionary stability," Journal of Economic Theory, Elsevier, vol. 230(C).
    3. Gagnon-Bartsch, Tristan & Bushong, Benjamin, 2022. "Learning with misattribution of reference dependence," Journal of Economic Theory, Elsevier, vol. 203(C).
    4. Philippe Jehiel & Erik Mohlin, 2023. "Categorization in Games: A Bias-Variance Perspective," Working Papers halshs-04154272, HAL.
    5. Clyde, Alexander, 2025. "Proxy variables and feedback effects in decision making," Games and Economic Behavior, Elsevier, vol. 153(C), pages 408-429.
    6. Ba, Cuimin & Gindin, Alice, 2023. "A multi-agent model of misspecified learning with overconfidence," Games and Economic Behavior, Elsevier, vol. 142(C), pages 315-338.
    7. Joel Vanden, 2015. "Noisy information and the size effect in stock returns," Annals of Finance, Springer, vol. 11(1), pages 77-107, February.
    8. J. Aislinn Bohren & Daniel N. Hauser, 2023. "Behavioral Foundations of Model Misspecification," PIER Working Paper Archive 23-007, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania.
    9. Daria Fedyaeva & Georgy Lukyanov & Hannah Tolli'e, 2025. "Learning to Unlearn: Education as a Remedy for Misspecified Beliefs," Papers 2510.24735, arXiv.org, revised Aug 2026.
    10. Mira Frick & Ryota Iijima & Yuhta Ishii, 2020. "Belief Convergence under Misspecified Learning: A Martingale Approach," Cowles Foundation Discussion Papers 2235R, Cowles Foundation for Research in Economics, Yale University, revised Mar 2021.
    11. Ignacio Esponda & Emanuel Vespa & Sevgi Yuksel, 2024. "Mental Models and Learning: The Case of Base-Rate Neglect," American Economic Review, American Economic Association, vol. 114(3), pages 752-782, March.
    12. García, Diego & Urošević, Branko, 2013. "Noise and aggregation of information in large markets," Journal of Financial Markets, Elsevier, vol. 16(3), pages 526-549.
    13. Chad Kendall & Ryan Oprea, 2024. "On the complexity of forming mental models," Quantitative Economics, Econometric Society, vol. 15(1), pages 175-211, January.
    14. Chen, Jaden Yang, 2022. "Biased learning under ambiguous information," Journal of Economic Theory, Elsevier, vol. 203(C).
    15. Scott Robertson, 2023. "Equilibrium with Heterogeneous Information Flows," Papers 2304.01272, arXiv.org, revised Mar 2024.
    16. Larry Samuelson & Jakub Steiner, 2024. "Robust latent data representations," ECON - Working Papers 460, Department of Economics - University of Zurich, revised Jul 2025.
    17. Nicolae Gârleanu & Lasse Heje Pedersen, 2018. "Efficiently Inefficient Markets for Assets and Asset Management," Journal of Finance, American Finance Association, vol. 73(4), pages 1663-1712, August.
    18. Anagnostidis, Panagiotis & Fontaine, Patrice & Varsakelis, Christos, 2020. "Are high–frequency traders informed?," Economic Modelling, Elsevier, vol. 93(C), pages 365-383.
    19. Verrecchia, Robert E., 2001. "Essays on disclosure," Journal of Accounting and Economics, Elsevier, vol. 32(1-3), pages 97-180, December.
    20. Doron Israeli & Ron Kasznik & Suhas A. Sridharan, 2022. "Unexpected distractions and investor attention to corporate announcements," Review of Accounting Studies, Springer, vol. 27(2), pages 477-518, June.

    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:2607.13670. 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: https://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.