A Survey of Methods for Explaining Black Box Models

In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

Data and Resources
To access the resources you must log in
  • PaperPDF

    The resource: 'Paper' is not accessible as guest user. You must login to access it!
  • DOI: 10.1145/3236009HTML

    The resource: 'DOI: 10.1145/3236009' is not accessible as guest user. You must login to access it!
  • BibTeXBibTeX

    The resource: 'BibTeX' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Author Guidotti, Riccardo,,
Author Monreale, Anna
Author Ruggieri, Salvatore
Author Turini, Franco
Author Giannotti, Fosca,
Author Pedreschi, Dino
Category Transparency and explanability
Publisher ACM New York, NY, USA
Source ACM Comput. Surv. 51, 5, Article 93 (January 2019), 42 pages
Thematic Cluster Other
system:type JournalArticle
Management Info
Field Value
Author Candela Leonardo
Maintainer Candela Leonardo
Version 1
Last Updated 19 July 2022, 15:51 (CEST)
Created 27 November 2020, 17:27 (CET)