Keeping designers in the loop: Communicating inherent algorithmic trade-offs across multiple objectives

Bowen Yu, Ye Yuan, Loren Terveen, Zhiwei Steven Wu, Jodi Forlizzi, Haiyi Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stake contexts. However, these algorithms are complex and have trade-offs, notably between prediction accuracy and fairness to population subgroups. This makes it hard for designers to understand algorithms and design products or services in a way that respects users' goals, values, and needs. We proposed a method to help designers and users explore algorithms, visualize their trade-offs, and select algorithms with trade-offs consistent with their goals and needs. We evaluated our method on the problem of predicting criminal defendants' likelihood to re-offend through (i) a large-scale Amazon Mechanical Turk experiment, and (ii) in-depth interviews with domain experts. Our evaluations show that our method can help designers and users of these systems better understand and navigate algorithmic trade-offs. This paper contributes a new way of providing designers the ability to understand and control the outcomes of algorithmic systems they are creating.

Original languageEnglish (US)
Title of host publicationDIS 2020 - Proceedings of the 2020 ACM Designing Interactive Systems Conference
PublisherAssociation for Computing Machinery, Inc
Pages1245-1257
Number of pages13
ISBN (Electronic)9781450369749
DOIs
StatePublished - Jul 3 2020
Event2020 ACM Conference on Designing Interactive Systems, DIS 2020 - Eindhoven, Netherlands
Duration: Jul 6 2020Jul 10 2020

Publication series

NameDIS 2020 - Proceedings of the 2020 ACM Designing Interactive Systems Conference

Conference

Conference2020 ACM Conference on Designing Interactive Systems, DIS 2020
Country/TerritoryNetherlands
CityEindhoven
Period7/6/207/10/20

Bibliographical note

Funding Information:
This work was supported by the National Science Foundation (NSF) under Award No. IIS-2001851 and No. IIS-2000782, the NSF Program on Fairness in AI in collaboration with Amazon under Award No. IIS-1939606, and the JP Morgan Faculty Award.

Publisher Copyright:
© 2020 ACM.

Keywords

  • Algorithmic fairness
  • Algorithmic trade-offs
  • Case study
  • Criminal prediction
  • Experimental design
  • Interactive visualization
  • Interview study

Fingerprint

Dive into the research topics of 'Keeping designers in the loop: Communicating inherent algorithmic trade-offs across multiple objectives'. Together they form a unique fingerprint.

Cite this