IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2309.13246.html
   My bibliography  Save this paper

Can I Trust the Explanations? Investigating Explainable Machine Learning Methods for Monotonic Models

Author

Listed:
  • Dangxing Chen

Abstract

In recent years, explainable machine learning methods have been very successful. Despite their success, most explainable machine learning methods are applied to black-box models without any domain knowledge. By incorporating domain knowledge, science-informed machine learning models have demonstrated better generalization and interpretation. But do we obtain consistent scientific explanations if we apply explainable machine learning methods to science-informed machine learning models? This question is addressed in the context of monotonic models that exhibit three different types of monotonicity. To demonstrate monotonicity, we propose three axioms. Accordingly, this study shows that when only individual monotonicity is involved, the baseline Shapley value provides good explanations; however, when strong pairwise monotonicity is involved, the Integrated gradients method provides reasonable explanations on average.

Suggested Citation

  • Dangxing Chen, 2023. "Can I Trust the Explanations? Investigating Explainable Machine Learning Methods for Monotonic Models," Papers 2309.13246, arXiv.org.
  • Handle: RePEc:arx:papers:2309.13246
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2309.13246
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Niklas Bussmann & Paolo Giudici & Dimitri Marinelli & Jochen Papenbrock, 2021. "Explainable Machine Learning in Credit Risk Management," Computational Economics, Springer;Society for Computational Economics, vol. 57(1), pages 203-216, January.
    2. Friedman, Eric & Moulin, Herve, 1999. "Three Methods to Share Joint Costs or Surplus," Journal of Economic Theory, Elsevier, vol. 87(2), pages 275-312, August.
    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. Yves Sprumont, 2010. "An Axiomatization of the Serial Cost-Sharing Method," Econometrica, Econometric Society, vol. 78(5), pages 1711-1748, September.
    2. Juarez, Ruben & Ko, Chiu Yu & Xue, Jingyi, 2018. "Sharing sequential values in a network," Journal of Economic Theory, Elsevier, vol. 177(C), pages 734-779.
    3. Hervé Moulin & Yves Sprumont, 2007. "Fair allocation of production externalities : recent results," Revue d'économie politique, Dalloz, vol. 117(1), pages 7-36.
    4. Hougaard, Jens Leth & Tind, Jørgen, 2009. "Cost allocation and convex data envelopment," European Journal of Operational Research, Elsevier, vol. 194(3), pages 939-947, May.
    5. Bastos, João A. & Matos, Sara M., 2022. "Explainable models of credit losses," European Journal of Operational Research, Elsevier, vol. 301(1), pages 386-394.
    6. Tang, Pan & Tang, Tiantian & Lu, Chennuo, 2024. "Predicting systemic financial risk with interpretable machine learning," The North American Journal of Economics and Finance, Elsevier, vol. 71(C).
    7. Zhou, Ying & Li, Haoran & Xiao, Zhi & Qiu, Jing, 2023. "A user-centered explainable artificial intelligence approach for financial fraud detection," Finance Research Letters, Elsevier, vol. 58(PA).
    8. Koster, M.A.L., 1998. "Multi-Service Serial Cost Sharing : A Characterization of the Moulin-Shenker Rule," Discussion Paper 1998-06, Tilburg University, Center for Economic Research.
    9. Friedman, Eric J., 2012. "Asymmetric Cost Sharing mechanisms," Games and Economic Behavior, Elsevier, vol. 75(1), pages 139-151.
    10. Robert John Kolesar & Peter Bogetoft & Vanara Chea & Guido Erreygers & Sambo Pheakdey, 2022. "Advancing universal health coverage in the COVID-19 era: an assessment of public health services technical efficiency and applied cost allocation in Cambodia," Health Economics Review, Springer, vol. 12(1), pages 1-20, December.
    11. Hougaard, Jens Leth & Moreno-Ternero, Juan D. & Tvede, Mich & Østerdal, Lars Peter, 2017. "Sharing the proceeds from a hierarchical venture," Games and Economic Behavior, Elsevier, vol. 102(C), pages 98-110.
    12. Eric Bahel & Christian Trudeau, 2018. "Consistency requirements and pattern methods in cost sharing problems with technological cooperation," International Journal of Game Theory, Springer;Game Theory Society, vol. 47(3), pages 737-765, September.
    13. Friedman, Eric J., 2002. "Strategic properties of heterogeneous serial cost sharing," Mathematical Social Sciences, Elsevier, vol. 44(2), pages 145-154, November.
    14. Chen, Yan, 2003. "An experimental study of serial and average cost pricing mechanisms," Journal of Public Economics, Elsevier, vol. 87(9-10), pages 2305-2335, September.
    15. Watts, Alison, 2002. "Uniqueness of equilibrium in cost sharing games," Journal of Mathematical Economics, Elsevier, vol. 37(1), pages 47-70, February.
    16. Wang, Yun-Tong & Zhu, Daxin, 2002. "Ordinal proportional cost sharing," Journal of Mathematical Economics, Elsevier, vol. 37(3), pages 215-230, May.
    17. Mariusz Kaleta & Eugeniusz Toczyłowski, 2009. "A cost allocation framework for LP and GLP games," Operations Research and Decisions, Wroclaw University of Science and Technology, Faculty of Management, vol. 19(4), pages 27-46.
    18. Koster, M.A.L., 1998. "Multi-Service Serial Cost Sharing : A Characterization of the Moulin-Shenker Rule," Other publications TiSEM 4d029e40-e4e7-4f90-b963-d, Tilburg University, School of Economics and Management.
    19. Kumar, Rajnish, 2013. "Secure implementation in production economies," Mathematical Social Sciences, Elsevier, vol. 66(3), pages 372-378.
    20. Moulin, Herve, 2002. "Axiomatic cost and surplus sharing," Handbook of Social Choice and Welfare, in: K. J. Arrow & A. K. Sen & K. Suzumura (ed.), Handbook of Social Choice and Welfare, edition 1, volume 1, chapter 6, pages 289-357, Elsevier.

    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:2309.13246. 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.