Interface design optimization as a multi-armed bandit problem

J. Derek Lomas, Jodi Forlizzi, Nikhil Poonwala, Nirmal Patel, Sharan Shodhan, Kishan Patel, Ken Koedinger, Emma Brunskill

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

37 Citations (Scopus)

Abstract

"Multi-armed bandits" offer a new paradigm for the AIassisted design of user interfaces. To help designers understand the potential, we present the results of two experimental comparisons between bandit algorithms and random assignment. Our studies are intended to show designers how bandits algorithms are able to rapidly explore an experimental design space and automatically select the optimal design configuration. Our present focus is on the optimization of a game design space. The results of our experiments show that bandits can make data-driven design more efficient and accessible to interface designers, but that human participation is essential to ensure that AI systems optimize for the right metric. Based on our results, we introduce several design lessons that help keep human design judgment in the loop. We also consider the future of human-technology teamwork in AI-assisted design and scientific inquiry. Finally, as bandits deploy fewer lowperforming conditions than typical experiments, we discuss ethical implications for bandits in large-scale experiments in education.

Original languageEnglish
Title of host publication34th Conference on Human Factors in Computing Systems, Proceedings
PublisherAssociation for Computing Machinery (ACM)
Pages4142-4153
Number of pages12
ISBN (Electronic)9781450333627
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event34th Annual Conference on Human Factors in Computing Systems, CHI 2016 - San Jose, United States
Duration: 7 May 201612 May 2016

Publication series

NameConference on Human Factors in Computing Systems - Proceedings
Volume0

Conference

Conference34th Annual Conference on Human Factors in Computing Systems, CHI 2016
Country/TerritoryUnited States
CitySan Jose
Period7/05/1612/05/16

Keywords

  • Continuous improvement
  • Data-driven design
  • Educational games
  • Multiarmed bandits
  • Optimization

Fingerprint

Dive into the research topics of 'Interface design optimization as a multi-armed bandit problem'. Together they form a unique fingerprint.

Cite this