IDEAS home Printed from https://ideas.repec.org/a/eee/jetheo/v221y2024ics0022053124000929.html

Learning from a black box

Author

Listed:
  • Ke, Shaowei
  • Wu, Brian
  • Zhao, Chen

Abstract

We introduce a learning model in which the decision maker does not know how recommendations are generated, called the contraction rule. We present behavioral postulates that characterize it. The contraction rule can be uniquely identified and reveals how the decision maker interprets and how much she trusts the recommendation. In a dynamic stationary setting, we show that the contraction rule is not dominated by completely following recommendations and is incompatible with a property called compliance with balanced recommendations. Following this negative result, we demonstrate that the contraction rule may generate and reinforce recency bias and disagreement.

Suggested Citation

  • Ke, Shaowei & Wu, Brian & Zhao, Chen, 2024. "Learning from a black box," Journal of Economic Theory, Elsevier, vol. 221(C).
    • Handle: RePEc:eee:jetheo:v:221:y:2024:i:c:s0022053124000929
    DOI: 10.1016/j.jet.2024.105886
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0022053124000929
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.jet.2024.105886?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
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Evan Sadler, 2021. "A Practical Guide to Updating Beliefs From Contradictory Evidence," Econometrica, Econometric Society, vol. 89(1), pages 415-436, January.
    2. Ke, Shaowei & Zhao, Chen, 2024. "From local utility to neural networks," Journal of Mathematical Economics, Elsevier, vol. 113(C).
    3. T Renee Bowen & Danil Dmitriev & Simone Galperti, 2023. "Learning from Shared News: When Abundant Information Leads to Belief Polarization," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 138(2), pages 955-1000.
    4. Simone Cerreia-Vioglio & Roberto Corrao & Giacomo Lanzani, 2024. "Dynamic Opinion Aggregation: Long-Run Stability and Disagreement," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 91(3), pages 1406-1447.
    5. Pietro Ortoleva, 2012. "Modeling the Change of Paradigm: Non-Bayesian Reactions to Unexpected News," American Economic Review, American Economic Association, vol. 102(6), pages 2410-2436, October.
    6. Gajdos, T. & Hayashi, T. & Tallon, J.-M. & Vergnaud, J.-C., 2008. "Attitude toward imprecise information," Journal of Economic Theory, Elsevier, vol. 140(1), pages 27-65, May.
    7. Sandeep Baliga & Eran Hanany & Peter Klibanoff, 2013. "Polarization and Ambiguity," American Economic Review, American Economic Association, vol. 103(7), pages 3071-3083, December.
    8. Chambers, Christopher P. & Hayashi, Takashi, 2010. "Bayesian consistent belief selection," Journal of Economic Theory, Elsevier, vol. 145(1), pages 432-439, January.
    9. Cesaltina Pacheco Pires, 2002. "A Rule For Updating Ambiguous Beliefs," Theory and Decision, Springer, vol. 53(2), pages 137-152, September.
    10. Pooya Molavi & Alireza Tahbaz‐Salehi & Ali Jadbabaie, 2018. "A Theory of Non‐Bayesian Social Learning," Econometrica, Econometric Society, vol. 86(2), pages 445-490, March.
    11. Benjamin Golub & Matthew O. Jackson, 2012. "How Homophily Affects the Speed of Learning and Best-Response Dynamics," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 127(3), pages 1287-1338.
    12. Peter M. DeMarzo & Dimitri Vayanos & Jeffrey Zwiebel, 2003. "Persuasion Bias, Social Influence, and Unidimensional Opinions," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 118(3), pages 909-968.
    13. Benjamin Golub & Matthew O. Jackson, 2010. "Naïve Learning in Social Networks and the Wisdom of Crowds," American Economic Journal: Microeconomics, American Economic Association, vol. 2(1), pages 112-149, February.
    14. Larry G. Epstein, 2006. "An Axiomatic Model of Non-Bayesian Updating," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 73(2), pages 413-436.
    15. Cheng, Xiaoyu, 2022. "Relative Maximum Likelihood updating of ambiguous beliefs," Journal of Mathematical Economics, Elsevier, vol. 99(C).
    16. Ravi Bansal & Ivan Shaliastovich, 2010. "Confidence Risk and Asset Prices," American Economic Review, American Economic Association, vol. 100(2), pages 537-541, May.
    17. Damiano Ettore, 2006. "Choice under Limited Uncertainty," The B.E. Journal of Theoretical Economics, De Gruyter, vol. 6(1), pages 1-37, September.
    18. Matthew Kovach, 2021. "Conservative Updating," Papers 2102.00152, arXiv.org.
    19. Zhao, Chen, 2022. "Pseudo-Bayesian updating," Theoretical Economics, Econometric Society, vol. 17(1), January.
    20. Park, Hyoeun & Tayawa, Jason Paulo, 2024. "Anchored belief updating from recommendations," Journal of Mathematical Economics, Elsevier, vol. 110(C).
    21. Jackson, Matthew O. & Zenou, Yves, 2015. "Games on Networks," Handbook of Game Theory with Economic Applications,, Elsevier.
    22. Jacopo Perego & Sevgi Yuksel, 2022. "Media Competition and Social Disagreement," Econometrica, Econometric Society, vol. 90(1), pages 223-265, January.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Paul H. Y. Cheung & Yusufcan Masatlioglu, 2025. "Frame-dependent Random Utility," Papers 2502.00209, arXiv.org.
    2. Yanagita, Shohei, 2025. "Overreacting to a black box," Journal of Mathematical Economics, Elsevier, vol. 118(C).
    3. Elchin Suleymanov, 2025. "Robust Maximum Likelihood Updating," Papers 2504.17151, arXiv.org, revised Dec 2025.
    4. Hsieh, Sung-Lin & Ke, Shaowei & Wang, Zhaoran & Zhao, Chen, 2025. "Logit neural-network utility," Journal of Economic Behavior & Organization, Elsevier, vol. 236(C).

    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. Elchin Suleymanov, 2025. "Robust Maximum Likelihood Updating," Papers 2504.17151, arXiv.org, revised Dec 2025.
    2. Yanagita, Shohei, 2025. "Overreacting to a black box," Journal of Mathematical Economics, Elsevier, vol. 118(C).
    3. Luo, Xiao & Qian, Xuewen, 2025. "Conditional hypothesis testing systems," Journal of Mathematical Economics, Elsevier, vol. 120(C).
    4. Margherita Comola & Agnieszka Rusinowska & Marie Claire Villeval, 2024. "Competing for Influence in Networks Through Strategic Targeting [En compétition pour l'influence dans les réseaux grâce au ciblage stratégique]," Working Papers hal-04706311, HAL.
    5. Fernandes, Marcos R., 2023. "Confirmation bias in social networks," Mathematical Social Sciences, Elsevier, vol. 123(C), pages 59-76.
    6. Buechel, Berno & Klößner, Stefan & Meng, Fanyuan & Nassar, Anis, 2023. "Misinformation due to asymmetric information sharing," Journal of Economic Dynamics and Control, Elsevier, vol. 150(C).
    7. Della Lena, Sebastiano, 2024. "The spread of misinformation in networks with individual and social learning," European Economic Review, Elsevier, vol. 168(C).
    8. Crès, Hervé & Tvede, Mich, 2022. "Aggregation of opinions in networks of individuals and collectives," Journal of Economic Theory, Elsevier, vol. 199(C).
    9. Levy, Gilat & Razin, Ronny, 2018. "Information diffusion in networks with the Bayesian Peer Influence heuristic," Games and Economic Behavior, Elsevier, vol. 109(C), pages 262-270.
    10. Ma, Jinling & Zhao, Chen, 2024. "Logic-based updating," Journal of Economic Theory, Elsevier, vol. 221(C).
    11. Andrea Galeotti & Benjamin Golub & Sanjeev Goyal & Rithvik Rao, 2021. "Discord and Harmony in Networks," Papers 2102.13309, arXiv.org.
    12. Larry Samuelson & Jakub Steiner, 2024. "Robust latent data representations," ECON - Working Papers 460, Department of Economics - University of Zurich, revised Jul 2025.
    13. Bolletta, Ugo & Pin, Paolo, 2025. "Dynamic opinion updating with endogenous networks," European Economic Review, Elsevier, vol. 176(C).
    14. Patacchini, Eleonora & Rainone, Edoardo & Zenou, Yves, 2017. "Heterogeneous peer effects in education," Journal of Economic Behavior & Organization, Elsevier, vol. 134(C), pages 190-227.
    15. Gallo, E. & Langtry, A., 2020. "Social Networks, Confirmation Bias and Shock Elections," Cambridge Working Papers in Economics 2099, Faculty of Economics, University of Cambridge.
    16. Eger, Steffen, 2016. "Opinion dynamics and wisdom under out-group discrimination," Mathematical Social Sciences, Elsevier, vol. 80(C), pages 97-107.
    17. Polanski, Arnold & Vega-Redondo, Fernando, 2023. "Homophily and influence," Journal of Economic Theory, Elsevier, vol. 207(C).
    18. Rapanos, Theodoros, 2023. "What makes an opinion leader: Expertise vs popularity," Games and Economic Behavior, Elsevier, vol. 138(C), pages 355-372.
    19. Brian Hill, 2022. "Updating confidence in beliefs," Post-Print hal-03503986, HAL.
    20. Hill, Brian, 2022. "Updating confidence in beliefs," Journal of Economic Theory, Elsevier, vol. 199(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:eee:jetheo:v:221:y:2024:i:c:s0022053124000929. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/inca/622869 .

    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.