Gender Bias and Property Taxes

2024-12-17

arXiv.org

AI Summary

This study investigates gender bias in property tax assessment hearings and its causal effect on appeal outcomes. Leveraging over 100,000 hearing records and 2.7 years of audio data, we employ multimodal large language models (M-LLMs) to extract prosodic and behavioral features, and apply rigorous causal inference and statistical modeling to estimate the causal impact of panel gender composition on assessed value reductions. Results reveal that female appellants face significantly lower overall success rates—and critically, receive *smaller* valuation reductions before all-female panels, a counterintuitive finding inconsistent with behavioral explanations. This suggests implicit stereotyping among reviewers, rather than appellant conduct, drives systematic bias. To our knowledge, this is the first study to empirically identify and causally attribute unspoken gender bias among administrative decision-makers in hearing contexts. It establishes a reproducible methodological framework for detecting latent discrimination in administrative big data using AI-driven multimodal analysis.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Gender bias distorts the economic behavior and outcomes of women and households. We investigate gender biases in property taxes. We analyze records of more than 100,000 property tax appeal hearings and more than 2.7 years of associated audio recordings, considering how panelist and appellant genders associate with hearing outcomes. We first observe that female appellants fare systematically worse than male appellants in their hearings. Second, we show that, whereas male appellants' hearing outcomes do not vary meaningfully with the gender composition of the panel they face, those of female appellants' do, such that female appellants obtain systematically lesser (greater) reductions to their home values when facing female (male) panelists. Employing a multi-modal large language model (M-LLM), we next construct measures of participant behavior and tone from hearing audio recordings. We observe markedly different behaviors between male and female appellants and, in the case of male appellants, we find that these differences also depend on the gender of the panelists they face (e.g., male appellants appear to behave systematically more aggressively towards female panelists). In contrast, the behavior of female appellants remains relatively constant, regardless of their panel's gender. Finally, we show that female appellants continue to fare worse in front of female panels, even when we condition upon the appelant's in-hearing behavior and tone. Our results are thus consistent with the idea that gender biases are driven, at least in part, by unvoiced beliefs and perceptions on the part of ARB panelists. Our study documents the presence of gender biases in property appraisal appeal hearings and highlights the potential value of generative AI for analyzing large-scale, unstructured administrative data.

Problem

• Gender bias in property taxes
• Impact of gender on hearing outcomes
• AI analysis of administrative data

Innovation

• Multi-modal large language model
• Analysis of audio recordings
• Gender bias detection