Conference Paper/Proceeding/Abstract 11 views
Raising User Awareness of Bias-Leakage via Proxies in AI Models to Improve Fairness in Decision-making
Peter Daish,
Matt Roach 
,
Alan Dix
,
Alan Dix
AISB Convention 2023, Pages: 86 - 88
Swansea University Authors:
Peter Daish, Matt Roach , Alan Dix
Abstract
Artificial Intelligence systems are becoming more common in decision-making, both for facilitating automated decisions or in tandem with human decision-makers as decisionsupport systems. AI-assisted DSS are typically employed to make data-driven recommendations to human decision-makers in an effort...
| Published in: | AISB Convention 2023 |
|---|---|
| ISBN: | 978-1-908187-85-7 |
| Published: |
2023
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa68368 |
| Abstract: |
Artificial Intelligence systems are becoming more common in decision-making, both for facilitating automated decisions or in tandem with human decision-makers as decisionsupport 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 datadriven 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 highstakes 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. |
|---|---|
| College: |
Faculty of Science and Engineering |
| Start Page: |
86 |
| End Page: |
88 |