Skip to main navigation Skip to search Skip to main content

Raising User Awareness of Bias-Leakage via Proxies in AI Models to Improve Fairness in Decision-making

  • Peter Daish
  • , Matt Roach
  • , Alan Dix

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Artificial Intelligence systems are becoming more common in decision-making, both for facilitating automated decisions or in tandem with human decision-makers as decision-support systems. AI-assisted DSS are typically employed to make data-driven recommendations to human decision-makers in an effort to improve efficiency and accuracy. In addition, the AI used to power DSS are typically blackbox in nature, meaning that human decision-makers are unaware of exactly how these systems are coming to their conclusions. This is problematic since research in algorithmic fairness already shows that data-driven AI systems can be influenced by social biases present in training data, to reinforce systemic biases and perpetuate unfairness towards minority social groups. When used in high-stakes decision-making, such systems risk protracting systemic biases and further driving social division. An area of research is emerging acknowledging that unfairness can leak through 'proxy' features, causing an implicit-bias effect. In this work-in-progress paper, we propose explaining fairness properties of AI systems and their downstream social impacts to decision-makers - by visualising bias-leakage through proxies - for improved fairness. Finally, we are currently in the process of conducting a study to empirically assess how visualising proxy-biases in AI-assisted DSS can affect decision-making and improve fairness.

Original languageEnglish
Title of host publicationProceedings of the AISB Convention 2023
EditorsBerndt Muller
PublisherThe Society for the Study of Artificial Intelligence and Simulation of Behaviour
Pages86-88
Number of pages3
ISBN (Electronic)9781713879466
Publication statusPublished - Apr 2023
Externally publishedYes
Event2023 Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour, AISB 2023 - Swansea, United Kingdom
Duration: 13 Apr 2023 → 14 Apr 2023

Publication series

NameProceedings of the AISB Convention 2023

Conference

Conference2023 Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour, AISB 2023
Country/TerritoryUnited Kingdom
CitySwansea
Period13/04/23 → 14/04/23

Keywords

  • bias-leakage
  • bias-visualisation
  • decision support system
  • downstream unfairness
  • fairness
  • machine learning
  • machine-bias
  • proxy

Cite this