IDEAS home Printed from https://ideas.repec.org/p/hal/journl/hal-05464751.html

Strategic Information Disclosure to Classification Algorithms: An Experiment

Author

Listed:
  • Jeanne Hagenbach

    (ECON - Département d'économie (Sciences Po) - Sciences Po - Sciences Po - CNRS - Centre National de la Recherche Scientifique, CNRS - Centre National de la Recherche Scientifique, WZB - Wissenschaftszentrum Berlin für Sozialforschung, CEPR - Center for Economic Policy Research)

  • Aurélien Salas

    (ECON - Département d'économie (Sciences Po) - Sciences Po - Sciences Po - CNRS - Centre National de la Recherche Scientifique)

Abstract

We experimentally study how individuals strategically disclose multidimensional information to a Naive Bayes algorithm trained to guess their characteristics. Subjects' objective is to minimize the algorithm's accuracy in guessing a target characteristic. We vary what participants know about the algorithm's functioning and how obvious are the correlations between the target and other characteristics. Optimal disclosure strategies rely on subjects identifying whether the combination of their characteristics is common or not. Information about the algorithm functioning makes subjects identify correlations they otherwise do not see but also overthink. Overall, this information decreases the frequency of optimal disclosure strategies.

Suggested Citation

  • Jeanne Hagenbach & Aurélien Salas, 2025. "Strategic Information Disclosure to Classification Algorithms: An Experiment," Post-Print hal-05464751, HAL.
    • Handle: RePEc:hal:journl:hal-05464751
    DOI: 10.1017/eec.2025.10030
    Note: View the original document on HAL open archive server: https://sciencespo.hal.science/hal-05464751v1
    as

    Download full text from publisher

    File URL: https://sciencespo.hal.science/hal-05464751v1/document
    Download Restriction: no
    File URL: https://libkey.io/10.1017/eec.2025.10030?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. Guillaume R. Fréchette & Emanuel Vespa & Sevgi Yuksel, 2025. "Extracting Statistical Relationships from Observational Data: Predicting with Full or Partial Information," AEA Papers and Proceedings, American Economic Association, vol. 115, pages 637-642, May.
    2. Andrea Wilson, 2014. "Bounded Memory and Biases in Information Processing," Econometrica, Econometric Society, vol. 82, pages 2257-2294, November.
    3. Eduardo Perez‐Richet & Vasiliki Skreta, 2022. "Test Design Under Falsification," Econometrica, Econometric Society, vol. 90(3), pages 1109-1142, May.
    4. Jeanne Hagenbach & Aurélien Salas, 2025. "Strategic Information Disclosure to Classification Algorithms: An Experiment," Post-Print hal-05464751, HAL.
    5. Alex Frankel & Navin Kartik, 2022. "Improving Information from Manipulable Data," Journal of the European Economic Association, European Economic Association, vol. 20(1), pages 79-115.
    6. Kfir Eliaz & Ran Spiegler, 2019. "The Model Selection Curse," American Economic Review: Insights, American Economic Association, vol. 1(2), pages 127-140, September.
    7. Marie-Pierre Dargnies & Rustamdjan Hakimov & Dorothea Kübler, 2026. "Aversion to Hiring Algorithms: Transparency, Gender Profiling, and Self-Confidence," Management Science, INFORMS, vol. 72(1), pages 285-301, January.
    8. Eliaz, Kfir & Spiegler, Ran, 2022. "On incentive-compatible estimators," Games and Economic Behavior, Elsevier, vol. 132(C), pages 204-220.
    9. Jeanine Miklós-Thal & Avi Goldfarb & Avery Haviv & Catherine Tucker, 2024. "Frontiers: Digital Hermits," Marketing Science, INFORMS, vol. 43(4), pages 697-708, July.
    10. Fréchette, Guillaume R & Vespa, Emanuel & Yuksel, Sevgi, 2025. "Extracting Statistical Relationships from Observational Data: Predicting with Full or Partial Information," University of California at San Diego, Economics Working Paper Series qt57x6d5sw, Department of Economics, UC San Diego.
    11. Leslie K. John & Alessandro Acquisti & George Loewenstein, 2011. "Strangers on a Plane: Context-Dependent Willingness to Divulge Sensitive Information," Journal of Consumer Research, Journal of Consumer Research Inc., vol. 37(5), pages 858-873.
    12. Berkeley J. Dietvorst & Joseph P. Simmons & Cade Massey, 2018. "Overcoming Algorithm Aversion: People Will Use Imperfect Algorithms If They Can (Even Slightly) Modify Them," Management Science, INFORMS, vol. 64(3), pages 1155-1170, March.
    13. Benjamin Enke & Florian Zimmermann, 2019. "Correlation Neglect in Belief Formation," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 86(1), pages 313-332.
    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. Jeanne Hagenbach & Aurélien Salas, 2025. "Strategic Information Disclosure to Classification Algorithms: An Experiment," Post-Print hal-05464751, HAL.

    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. Bó, Inácio & Chen, Li & Hakimov, Rustamdjan, 2024. "Strategic responses to personalized pricing and demand for privacy: An experiment," Games and Economic Behavior, Elsevier, vol. 148(C), pages 487-516.
    2. Tsakas, Elias & Tsakas, Nikolas, 2021. "Noisy persuasion," Games and Economic Behavior, Elsevier, vol. 130(C), pages 44-61.
    3. Bohren, Noah & Hakimov, Rustamdjan & Lalive, Rafael, 2024. "Creative and Strategic Capabilities of Generative AI: Evidence from Large-Scale Experiments," IZA Discussion Papers 17302, IZA Network @ LISER.
    4. Radosveta Ivanova-Stenzel & Michel Tolksdorf, 2025. "Delegating in the Age of AI: Preferences for Decision Autonomy," Rationality and Competition Discussion Paper Series 558, CRC TRR 190 Rationality and Competition.
    5. Aislinn Bohren & Daniel Hauser, 2017. "Bounded Rationality And Learning: A Framwork and A Robustness Result," PIER Working Paper Archive 17-007, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, revised 01 May 2017.
    6. Tan, Teck Yong, 2023. "Optimal transparency of monitoring capability," Journal of Economic Theory, Elsevier, vol. 209(C).
    7. Ivanova-Stenzel, Radosveta & Tolksdorf, Michel, 2024. "Measuring preferences for algorithms — How willing are people to cede control to algorithms?," Journal of Behavioral and Experimental Economics (formerly The Journal of Socio-Economics), Elsevier, vol. 112(C).
    8. Aislinn Bohren & Daniel Hauser, 2018. "Social Learning with Model Misspeciification: A Framework and a Robustness Result," PIER Working Paper Archive 18-017, Penn Institute for Economic Research, Department of Economics, University of Pennsylvania, revised 01 Jul 2018.
    9. Mallory Avery & Andreas Leibbrandt & Joseph Vecci, 2023. "Does Artificial Intelligence Help or Hurt Gender Diversity? Evidence from Two Field Experiments on Recruitment in Tech," Monash Economics Working Papers 2023-09, Monash University, Department of Economics.
    10. Bohren, Aislinn & Hauser, Daniel, 2017. "Learning with Heterogeneous Misspecified Models: Characterization and Robustness," CEPR Discussion Papers 12036, C.E.P.R. Discussion Papers.
    11. Benson Tsz Kin Leung, 2020. "Learning in a Small/Big World," Papers 2009.11917, arXiv.org, revised Mar 2023.
    12. Ivanova-Stenzel, Radosveta & Tolksdorf, Michel, 2023. "Measuring Preferences for Algorithms - Are people really algorithm averse after seeing the algorithm perform?," VfS Annual Conference 2023 (Regensburg): Growth and the "sociale Frage" 277692, Verein für Socialpolitik / German Economic Association.
    13. Leung, B. T. K., 2020. "Learning in a Small/Big World," Cambridge Working Papers in Economics 2085, Faculty of Economics, University of Cambridge.
    14. 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.
    15. Silvia Martinez-Gorricho & Carlos Oyarzun, 2024. "Testing under information manipulation," Economic Theory, Springer;Society for the Advancement of Economic Theory (SAET), vol. 77(3), pages 849-890, May.
    16. Yingkai Li & Boli Xu, 2024. "Learning and Communication Towards Unanimous Consent," Papers 2405.18521, arXiv.org, revised Feb 2026.
    17. Evan Piermont, 2021. "Hypothetical Expected Utility," Papers 2106.15979, arXiv.org, revised Jul 2021.
    18. Maxime Perodaud & Michela Chessa, 2026. "Hey, what did you expect ? Confirmation bias in credence goods markets: Theoretical and experimental analyses," Post-Print hal-05441370, HAL.
    19. Makarewicz, Tomasz, 2021. "Traders, forecasters and financial instability: A model of individual learning of anchor-and-adjustment heuristics," Journal of Economic Behavior & Organization, Elsevier, vol. 190(C), pages 626-673.
    20. Sweldens, Steven & Puntoni, Stefano & Paolacci, Gabriele & Vissers, Maarten, 2014. "The bias in the bias: Comparative optimism as a function of event social undesirability," Organizational Behavior and Human Decision Processes, Elsevier, vol. 124(2), pages 229-244.

    More about this item

    Keywords

    ;
    ;
    ;
    ;

    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:hal:journl:hal-05464751. 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: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    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.