IDEAS home Printed from https://ideas.repec.org/p/mse/cesdoc/20012.html
   My bibliography  Save this paper

A Note on the Interpretability of Machine Learning Algorithms

Author

Abstract

We are interested in the analysis of the concept of interpretability associated with a ML algorithm. We distinguish between the "How", i.e., how a black box or a very complex algorithm works, and the "Why", i.e. why an algorithm produces such a result. These questions appeal to many actors, users, professions, regulators among others. Using a formal standardized framework, we indicate the solutions that exist by specifying which elements of the supply chain are impacted when we provide answers to the previous questions. This presentation, by standardizing the notations, allows to compare the different approaches and to highlight the specificities of each of them: both their objective and their process. The study is not exhaustive and the subject is far from being closed

Suggested Citation

  • Dominique Guégan, 2020. "A Note on the Interpretability of Machine Learning Algorithms," Documents de travail du Centre d'Economie de la Sorbonne 20012, Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne.
  • Handle: RePEc:mse:cesdoc:20012
    as

    Download full text from publisher

    File URL: http://mse.univ-paris1.fr/pub/mse/CES2020/20012.pdf
    Download Restriction: no

    File URL: https://halshs.archives-ouvertes.fr/halshs-02900929
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Alexis Bogroff & Dominique Guegan, 2019. "Artificial Intelligence, Data, Ethics: An Holistic Approach for Risks and Regulation," Post-Print halshs-02181597, HAL.
    2. Igor Linkov & Benjamin D. Trump & Kelsey Poinsatte-Jones & Marie-Valentine Florin, 2018. "Governance Strategies for a Sustainable Digital World," Sustainability, MDPI, vol. 10(2), pages 1-8, February.
    3. Alexis Bogroff & Dominique Guégan, 2019. "Artificial Intelligence, Data, Ethics: An Holistic Approach for Risks and Regulation," Documents de travail du Centre d'Economie de la Sorbonne 19012, Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne.
    4. Alexis Bogroff & Dominique Guégan, 2019. "Artificial Intelligence, Data, Ethics. An Holistic Approach for Risks and Regulation," Working Papers 2019: 19, Department of Economics, University of Venice "Ca' Foscari".
    5. Alexis Bogroff & Dominique Guegan, 2019. "Artificial Intelligence, Data, Ethics: An Holistic Approach for Risks and Regulation," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) halshs-02181597, HAL.
    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. Dominique Guegan, 2020. "A Note on the Interpretability of Machine Learning Algorithms," Post-Print halshs-02900929, HAL.
    2. Dominique Guégan, 2020. "A Note on the Interpretability of Machine Learning Algorithms," Working Papers 2020:20, Department of Economics, University of Venice "Ca' Foscari".
    3. Dominique Guegan, 2020. "A Note on the Interpretability of Machine Learning Algorithms," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) halshs-02900929, HAL.
    4. Becker, Jörg & Distel, Bettina & Grundmann, Matthias & Hupperich, Thomas & Kersting, Norbert & Löschel, Andreas & Parreira do Amaral, Marcelo & Scholta, Hendrik, 2021. "Challenges and potentials of digitalisation for small and mid-sized towns: Proposition of a transdisciplinary research agenda," ERCIS Working Papers 36, University of Münster, European Research Center for Information Systems (ERCIS).
    5. Lingxiang Jian & Shuxuan Guo & Shengqing Yu, 2023. "Effect of Artificial Intelligence on the Development of China’s Wholesale and Retail Trade," Sustainability, MDPI, vol. 15(13), pages 1-19, July.
    6. Jean-David Fermanian & Dominique Guégan, 2021. "Fair learning with bagging," Documents de travail du Centre d'Economie de la Sorbonne 21034, Université Panthéon-Sorbonne (Paris 1), Centre d'Economie de la Sorbonne.
    7. Albérico Travassos Rosário & Joana Carmo Dias, 2023. "The New Digital Economy and Sustainability: Challenges and Opportunities," Sustainability, MDPI, vol. 15(14), pages 1-23, July.
    8. Gabriela Viale Pereira & Elsa Estevez & Diego Cardona & Carlos Chesñevar & Pablo Collazzo-Yelpo & Maria Alexandra Cunha & Eduardo Henrique Diniz & Alex Antonio Ferraresi & Frida Marina Fischer & Flúvi, 2020. "South American Expert Roundtable: Increasing Adaptive Governance Capacity for Coping with Unintended Side Effects of Digital Transformation," Sustainability, MDPI, vol. 12(2), pages 1-47, January.
    9. Lei Zhou & Qing Xia & Huaping Sun & Ling Zhang & Xu Jin, 2023. "The Role of Digital Transformation in High-Quality Development of the Services Trade," Sustainability, MDPI, vol. 15(5), pages 1-16, February.
    10. Araz Taeihagh, 2021. "Governance of artificial intelligence [Application of artificial intelligence for development of intelligent transport system in smart cities]," Policy and Society, Darryl S. Jarvis and M. Ramesh, vol. 40(2), pages 137-157.
    11. Chunyu Zhang & Wenge Zeng, 2024. "Evaluating the Construction of a Digital Supervision Platform for Digital Trade Systems: a Multilateral Perspective," Journal of the Knowledge Economy, Springer;Portland International Center for Management of Engineering and Technology (PICMET), vol. 15(3), pages 12503-12534, September.
    12. Rao, Amar & Talan, Amogh & Abbas, Shujaat & Dev, Dhairya & Taghizadeh-Hesary, Farhad, 2023. "The role of natural resources in the management of environmental sustainability: Machine learning approach," Resources Policy, Elsevier, vol. 82(C).
    13. Jean-David Fermanian & Dominique Guegan, 2021. "Fair learning with bagging," Post-Print halshs-03500906, HAL.
    14. Olivera Kostoska & Ljupco Kocarev, 2019. "A Novel ICT Framework for Sustainable Development Goals," Sustainability, MDPI, vol. 11(7), pages 1-31, April.
    15. Liliana Ionescu-Feleagă & Bogdan-Ștefan Ionescu & Oana Cristina Stoica, 2022. "The Impact of Digitalization on Happiness: A European Perspective," Mathematics, MDPI, vol. 10(15), pages 1-24, August.
    16. Oleg A. Kryzhanovskij & Natalia A. Baburina & Anastasia O. Ljovkina, 2021. "How to Make Digitalization Better Serve an Increasing Quality of Life?," Sustainability, MDPI, vol. 13(2), pages 1-11, January.
    17. Tai Ming Wut & Daisy Lee & Wai Man Ip & Stephanie W. Lee, 2021. "Digital Sustainability in the Organization: Scale Development and Validation," Sustainability, MDPI, vol. 13(6), pages 1-14, March.
    18. Daniela Roxana Vuță & Eliza Nichifor & Ioana Bianca Chițu & Gabriel Brătucu, 2022. "Digital Transformation—Top Priority in Difficult Times: The Case Study of Romanian Micro-Enterprises and SMEs," Sustainability, MDPI, vol. 14(17), pages 1-14, August.
    19. Ibinceanu Onica Mihaela Cristina & Cristache Nicoleta & Dobrea Răzvan Cătălin & Florescu Margareta, 2021. "Regional Development in Romania: Empirical Evidence Regarding the Factors for Measuring a Prosperous and Sustainable Economy," Sustainability, MDPI, vol. 13(7), pages 1-19, April.
    20. Mudalige Uthpala Indeelinie Alahakoon & Shahzadah Nayyar Jehan, 2020. "Efficiency of Public Service Delivery—A Post-ICT Deployment Analysis," Economies, MDPI, vol. 8(4), pages 1-13, November.

    More about this item

    Keywords

    Agnostic models; Artificial Intelligence; Counterfactual approach; Interpretability; LIME method; Machine learning;
    All these keywords.

    JEL classification:

    • C - Mathematical and Quantitative Methods
    • K - Law and Economics

    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:mse:cesdoc:20012. 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: Lucie Label (email available below). General contact details of provider: https://edirc.repec.org/data/cenp1fr.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.