Ethics and Information Technology 23 (3):253-263 (2020)

Authors
Michele Loi
Luiss Guido Carli
Abstract
In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand of the explainee. Finally, we argue that when models that pursue justifiable goals to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.
Keywords No keywords specified (fix it)
Categories (categorize this paper)
ISBN(s)
DOI 10.1007/s10676-020-09564-w
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy


Upload a copy of this paper     Check publisher's policy     Papers currently archived: 69,979
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

Anarchy, State, and Utopia.Robert Nozick - 1974 - New York: Basic Books.
Anarchy, State, and Utopia.Robert Nozick - 1974 - Philosophy 52 (199):102-105.
Political Liberalism.J. Rawls - 1995 - Tijdschrift Voor Filosofie 57 (3):596-598.

View all 15 references / Add more references

Citations of this work BETA

View all 6 citations / Add more citations

Similar books and articles

Democratizing Algorithmic Fairness.Pak-Hang Wong - 2020 - Philosophy and Technology 33 (2):225-244.
Ethical Implications and Accountability of Algorithms.Kirsten Martin - 2018 - Journal of Business Ethics 160 (4):835-850.
Is There an Ethics of Algorithms?Martin Peterson - 2011 - Ethics and Information Technology 13 (3):251-260.
On Logic of Complex Algorithms.Helena Rasiowa - 1981 - Studia Logica 40 (3):289 - 310.
What We Informationally Owe Each Other.Alan Rubel, Clinton Castro & Adam Pham - forthcoming - In Algorithms & Autonomy: The Ethics of Automated Decision Systems. Cambridge University Press: Cambridge University Press. pp. 21-42.

Analytics

Added to PP index
2020-10-21

Total views
19 ( #581,781 of 2,504,871 )

Recent downloads (6 months)
2 ( #277,627 of 2,504,871 )

How can I increase my downloads?

Downloads

My notes