Transparency As Design Publicity: Explaining and Justifying Inscrutable Algorithms

20 Pages Posted: 20 Jun 2019

See all articles by Michele Loi

Michele Loi

University of Zurich

Andrea Ferrario

Dep. Management, Technology, and Economics ETH Zurich; Mobiliar Lab for Analytics at ETH

Eleonora Viganò

University of Zurich - Institute for Biomedical Ethics and the History of Medicine

Date Written: June 14, 2019

Abstract

In this paper we argue that transparency, 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 (post-hoc) interpretable. These approaches 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 transparency, that consists in explaining the artifact as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance), and that provides a measure of the extent to which such goal is achieved, and evidence about the way that measure has been reached. We call such idea of 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. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.

Keywords: algorithms, transparency, interpretability, explanation, justification, AI

Suggested Citation

Loi, Michele and Ferrario, Andrea and Viganò, Eleonora, Transparency As Design Publicity: Explaining and Justifying Inscrutable Algorithms (June 14, 2019). Available at SSRN: https://ssrn.com/abstract=3404040 or http://dx.doi.org/10.2139/ssrn.3404040

Michele Loi (Contact Author)

University of Zurich ( email )

Rämistrasse 71
Zürich, CH-8006
Switzerland

Andrea Ferrario

Dep. Management, Technology, and Economics ETH Zurich ( email )

Mobiliar Lab for Analytics at ETH ( email )

Zürich, 8092
Switzerland

Eleonora Viganò

University of Zurich - Institute for Biomedical Ethics and the History of Medicine ( email )

Winterthurerstrasse 30
8006
Zürich, 8006
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
27
Abstract Views
238
PlumX Metrics