Effects of Algorithmic Decision-Making and Interpretability on Human Behavior: Experiments using Crowdsourcing

verfasst von

Avishek Anand, Kilian Bizer, Alexander Erlei, Ujwal Gadiraju, Christian Heinze, Lukas Meub, Wolfgang Nejdl, Björn Steinrötter

Abstract

Today algorithmic decision-making (ADM) is prevalent in several fields including medicine, the criminal justice system, financial markets etc. On the one hand, this is testament to the ever improving performance and capabilities of complex machine learning models. On the other hand, the increased complexity has resulted in a lack of transparency and interpretability which has led to critical decision-making models being deployed as functional black boxes. There is a general consensus that being able to explain the actions of such systems will help to address legal issues like transparency (ex ante) and compliance requirements (interim) as well as liability (ex post). Moreover it may build trust, expose biases and in turn lead to improved models. This has most recently led to research on extracting post-hoc explanations from black box classifiers and sequence generators in tasks like image captioning, text classification and machine translation. However, there is no work yet that has investigated and revealed the impact of model explanations on the nature of human decision-making. We undertake a large scale study using crowd-sourcing as a means to measure how interpretability affects human-decision making using well understood principles of behavioral economics. To our knowledge this is the first of its kind of an inter-disciplinary study involving interpretability in ADM models.

Organisationseinheit(en)

Forschungszentrum L3S
Institut für Rechtsinformatik (IRI)

Externe Organisation(en)

Georg-August-Universität Göttingen

Typ

Konferenzaufsatz in Fachzeitschrift

Journal

CEUR Workshop Proceedings

Band

2173

ISSN

1613-0073

Publikationsdatum

2018

Publikationsstatus

Veröffentlicht

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Informatik (insg.)

Ziele für nachhaltige Entwicklung

SDG 3 – Gute Gesundheit und Wohlergehen, SDG 16 – Frieden, Gerechtigkeit und starke Institutionen

Elektronische Version(en)

http://ceur-ws.org/Vol-2173/paper5.pdf (Zugang: Offen)