FairFuse: Interactive Visual Support for Fair Consensus Ranking
Preprint
Abstract
Fair consensus building combines the preferences of multiple rankers into a single consensus ranking, while ensuring any group defined by a protected attribute (such as race or gender) is not disadvantaged compared to other groups. Manually generating a fair consensus ranking is time-consuming and impractical -- even for a fairly small number of candidates. While algorithmic approaches for auditing and generating fair consensus rankings have been developed, these have not been operationalized in interactive systems. To bridge this gap, we introduce FairFuse, a visualization system for generating, analyzing, and auditing fair consensus rankings. We construct a data model which includes base rankings entered by rankers, augmented with measures of group fairness, and algorithms for generating consensus rankings with varying degrees of fairness. We design novel visualizations that encode these measures in a parallel-coordinates style rank visualization, with interactions for generating and exploring fair consensus rankings. We describe use cases in which FairFuse supports a decision-maker in ranking scenarios in which fairness is important, and discuss emerging challenges for future efforts supporting fairness-oriented rank analysis. Code and demo videos available at https://osf.io/hd639/.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- FairSight: Visual Analytics for Fairness in Decision MakingIEEE Transactions on Visualization and Computer Graphics, 2019
- SRVis: Towards Better Spatial Integration in Ranking VisualizationIEEE Transactions on Visualization and Computer Graphics, 2018
- Themis-ml: A Fairness-Aware Machine Learning Interface for End-To-End Discrimination Discovery and MitigationJournal of Technology in Human Services, 2018
- Bridging from Goals to Tasks with Design Study Analysis ReportsIEEE Transactions on Visualization and Computer Graphics, 2017
- LineUp: Visual Analysis of Multi-Attribute RankingsIEEE Transactions on Visualization and Computer Graphics, 2013
- Taxonomy-Based Glyph Design—with a Case Study on Visualizing Workflows of Biological ExperimentsIEEE Transactions on Visualization and Computer Graphics, 2012
- Empirical Studies in Information Visualization: Seven ScenariosIEEE Transactions on Visualization and Computer Graphics, 2011
- A new method for scoring additive multi‐attribute value models using pairwise rankings of alternativesJournal of Multi-Criteria Decision Analysis, 2008
- Web-Hipre: Global Decision Support By Value Tree And AHP AnalysisINFOR: Information Systems and Operational Research, 2000
- Voting schemes for which it can be difficult to tell who won the electionSocial Choice and Welfare, 1989