Bethany Hsiao, PhD Candidate in Operations, Information and Decisions, The Wharton School; Aaron Roth, Computer and Information Science, Penn Engineering; Michael Kearns, Computer and Information Science, Penn Engineering; Duncan Watts, Operations, Information and Decisions, The Wharton School; Hamsa Bastani, Operations, Information and Decisions, The Wharton School
Abstract: In algorithmic decision-making, it is often mathematically impossible to satisfy competing definitions of fairness simultaneously. This impossibility makes assessing stakeholders’ fairness preferences a challenging but crucial exercise. To address this, the researchers developed an interactive tool to elicit fairness preferences by projecting the complex decision space into a simple one-dimensional choice: setting risk thresholds. This design allows participants to directly manipulate algorithm parameters and visualize the resulting tradeoffs between competing fairness metrics. Participants’ decisions enable the researchers to study (1) what Pareto-optimal settings are perceived as fair and (2) whether the design of the elicitation process itself can fundamentally shape how fairness is perceived.