Tradeoffs are Domain Dependent: Improving Accuracy and Fairness in Property Tax Assessments
For policymakers and practitioners in public sector systems, this work demonstrates that domain-specific modeling improvements can advance both fairness and accuracy, countering the common belief in a universal tradeoff.
The paper challenges the assumed fairness-accuracy tradeoff in algorithmic fairness, showing that in U.S. property tax assessments, improvements in accuracy are strongly correlated with improvements in fairness across counties, and that adding features or public data can improve both simultaneously.
Algorithmic fairness research often assumes a tradeoff between fairness and accuracy. Yet this tradeoff may not be universal. We test this assumption in the context of U.S. property tax assessment - a setting in which the output of predictive algorithms directly determines the distribution of tax obligations among homeowners. Currently, systematic assessment errors cause owners of lower-valued properties to face disproportionately high tax burdens, creating regressivity in the property tax system. Using data on 26 million property sales spanning 95% of U.S. counties, we conduct three complementary analyses. First, we find that assessment accuracy and fairness - measured using domain-relevant metrics - are strongly correlated across counties under status quo practices. Second, in simulated assessment models, we show that adding property features improves accuracy in most cases, and that when accuracy improves, fairness almost always improves as well. Third, we show that incorporating publicly available Census data into assessment models - a feasible reform in most counties - would significantly improve both accuracy and fairness relative to status quo assessments. Together, these results challenge the presumed universality of the fairness-accuracy tradeoff and demonstrate that well-designed modeling improvements can advance both fairness and accuracy in large-scale public sector systems.