IDEAS home Printed from https://ideas.repec.org/p/ehl/lserod/120114.html
   My bibliography  Save this paper

Model-agnostic auditing: a lost cause?

Author

Listed:
  • Hansen, Sakina
  • Loftus, Joshua

Abstract

Tools for interpretable machine learning (IML) or explainable artificial intelligence (xAI) can be used to audit algorithms for fairness or other desiderata. In a black-box setting without access to the algorithm’s internal structure an auditor may be limited to methods that are model-agnostic. These methods have severe limitations with important consequences for outcomes such as fairness. Among model-agnostic IML methods, visualizations such as the partial dependence plot (PDP) or individual conditional expectation (ICE) plots are popular and useful for displaying qualitative relationships. Although we focus on fairness auditing with PDP/ICE plots, the consequences we highlight generalize to other auditing or IML/xAI applications. This paper questions the validity of auditing in high-stakes settings with contested values or conflicting interests if the audit methods are model-agnostic.

Suggested Citation

  • Hansen, Sakina & Loftus, Joshua, 2023. "Model-agnostic auditing: a lost cause?," LSE Research Online Documents on Economics 120114, London School of Economics and Political Science, LSE Library.
  • Handle: RePEc:ehl:lserod:120114
    as

    Download full text from publisher

    File URL: http://eprints.lse.ac.uk/120114/
    File Function: Open access version.
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. David M. Cutler & Adriana Lleras-Muney & Tom Vogl, 2008. "Socioeconomic Status and Health: Dimensions and Mechanisms," NBER Working Papers 14333, National Bureau of Economic Research, Inc.
    2. Aislinn Kelly-Lyth, 2021. "Challenging Biased Hiring Algorithms," Oxford Journal of Legal Studies, Oxford University Press, vol. 41(4), pages 899-928.
    3. Qingyuan Zhao & Trevor Hastie, 2021. "Causal Interpretations of Black-Box Models," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 39(1), pages 272-281, January.
    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. repec:zbw:rwirep:0119 is not listed on IDEAS
    2. Raquel Fonseca Benito & Yuhui Zheng, 2011. "The Effect of Education on Health Cross-Country Evidence," Working Papers WR-864, RAND Corporation.
    3. McInnis, Nicardo, 2023. "Long-term health effects of childhood parental income," Social Science & Medicine, Elsevier, vol. 317(C).
    4. Stefan Angel & Benjamin Bittschi, 2019. "Housing and Health," Review of Income and Wealth, International Association for Research in Income and Wealth, vol. 65(3), pages 495-513, September.
    5. Gerdtham, Ulf-G & Lundborg, Petter & Lyttkens, Carl Hampus & Nystedt, Paul, 2012. "Do Socioeconomic Factors Really Explain Income-Related Inequalities in Health? Applying a Twin Design to Standard Decomposition Analysis," Working Papers 2012:21, Lund University, Department of Economics.
    6. Emilio Aguirre & Federico García-Suárez & Gabriela Sicilia, 2021. "Eficiencia técnica en la ganadería de carne bovina pastoril. Medición y exploración de sus determinantes en Uruguay," Documentos de Trabajo (working papers) 1321, Department of Economics - dECON.
    7. Anthony Lepinteur, 2021. "The asymmetric experience of gains and losses in job security on health," Health Economics, John Wiley & Sons, Ltd., vol. 30(9), pages 2217-2229, September.
    8. Felix C.H. Gottschalk, 2019. "Why prevent when it does not pay? Prevention when health services are credence goods," Health Economics, John Wiley & Sons, Ltd., vol. 28(5), pages 693-709, May.
    9. Giorgio Brunello & Margherita Fort & Nicole Schneeweis & Rudolf Winter‐Ebmer, 2016. "The Causal Effect of Education on Health: What is the Role of Health Behaviors?," Health Economics, John Wiley & Sons, Ltd., vol. 25(3), pages 314-336, March.
    10. Loftus, Joshua R., 2024. "Position: the causal revolution needs scientific pragmatism," LSE Research Online Documents on Economics 125578, London School of Economics and Political Science, LSE Library.
    11. Yamin Du & Huanhuan Cheng & Qing Liu & Song Tan, 2024. "The delayed and combinatorial response of online public opinion to the real world: An inquiry into news texts during the COVID-19 era," Palgrave Communications, Palgrave Macmillan, vol. 11(1), pages 1-18, December.
    12. Anderberg, Dan & Chevalier, Arnaud & Wadsworth, Jonathan, 2011. "Anatomy of a health scare: Education, income and the MMR controversy in the UK," Journal of Health Economics, Elsevier, vol. 30(3), pages 515-530, May.
    13. Liping Fu & Ya’nan Fang & Yongqing Dong, 2022. "The healthcare inequality among middle-aged and older adults in China: a comparative analysis between the full samples and the homogeneous population," Health Economics Review, Springer, vol. 12(1), pages 1-17, December.
    14. Christoph Schwierz & Ansgar Wübker, 2009. "Determinants of Avoidable Deaths from Ischaemic Heart Diseases in East and West Germany," Ruhr Economic Papers 0119, Rheinisch-Westfälisches Institut für Wirtschaftsforschung, Ruhr-Universität Bochum, Universität Dortmund, Universität Duisburg-Essen.
    15. van Kippersluis, Hans & O'Donnell, Owen & van Doorslaer, Eddy & Van Ourti, Tom, 2010. "Socioeconomic differences in health over the life cycle in an Egalitarian country," Social Science & Medicine, Elsevier, vol. 70(3), pages 428-438, February.
    16. Chen, Yong & Lu, Zhiyuan & Liu, Heng & Wang, Hu & Zheng, Zunqing & Wang, Changhui & Sun, Xingyu & Xu, Linxun & Yao, Mingfa, 2024. "Machine learning-based design of target property-oriented fuels using explainable artificial intelligence," Energy, Elsevier, vol. 300(C).
    17. Stefano Cabras & J. D. Tena, 2023. "Implicit institutional incentives and individual decisions: Causal inference with deep learning models," Managerial and Decision Economics, John Wiley & Sons, Ltd., vol. 44(6), pages 3739-3754, September.
    18. Bastian Ravesteijn & Hans van Kippersluis & Eddy van Doorslaer, 2018. "The wear and tear on health: What is the role of occupation?," Health Economics, John Wiley & Sons, Ltd., vol. 27(2), pages 69-86, February.
    19. Jürgen Maurer, 2016. "Inspecting the Mechanism," Medical Decision Making, , vol. 36(7), pages 887-899, October.
    20. Madadkhani, Shiva & Ikonnikova, Svetlana, 2024. "Toward high-resolution projection of electricity prices: A machine learning approach to quantifying the effects of high fuel and CO2 prices," Energy Economics, Elsevier, vol. 129(C).
    21. Leen Sebrechts & Jef Breda, 2012. "Families of children with special needs in Flanders: their vulnerability within the citizenship paradigm," Working Papers 1201, Herman Deleeck Centre for Social Policy, University of Antwerp.

    More about this item

    Keywords

    artificial intelligence; black-box auditing; causal models; CEUR Workshop Proceedings (CEUR-WS.org); counterfactual fairness; individual conditional expectation; machine learning; partial dependence plots; supervised learning; visualization;
    All these keywords.

    JEL classification:

    • C1 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General

    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:ehl:lserod:120114. 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: LSERO Manager (email available below). General contact details of provider: https://edirc.repec.org/data/lsepsuk.html .

    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.