How Do Fair Decisions Fare in Long-term Qualification?
arXiv:2010.11300
Abstract
Although many fairness criteria have been proposed for decision making, their long-term impact on the well-being of a population remains unclear. In this work, we study the dynamics of population qualification and algorithmic decisions under a partially observed Markov decision problem setting. By characterizing the equilibrium of such dynamics, we analyze the long-term impact of static fairness constraints on the equality and improvement of group well-being. Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions. We also consider possible interventions that can effectively improve group qualification or promote equality of group qualification. Our theoretical results and experiments on static real-world datasets with simulated dynamics show that our framework can be used to facilitate social science studies.
arXiv commentAccepted to the 34th Conference on Neural Information Processing Systems (NeurIPS)
References in corpus (11)
- How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility
- Fairness Without Demographics in Repeated Loss Minimization
- Fairness in Learning: Classic and Contextual Bandits
- The Disparate Effects of Strategic Manipulation
- Optimal Decision Making Under Strategic Behavior
- On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning
- Achieving Fairness in the Stochastic Multi-armed Bandit Problem
- Fair Decisions Despite Imperfect Predictions
- Combinatorial Sleeping Bandits with Fairness Constraints
- Dynamic Modeling and Equilibria in Fair Decision Making
- Bandit Learning with Delayed Impact of Actions