Mind the Gaps: Auditing and Reducing Group Inequity in Large-Scale Mobility Prediction

2025-10-30

AI Summary

This study uncovers implicit racial/ethnic unfairness in large-scale mobile prediction models—manifested as systematic performance disparities across demographic groups. To address this, we propose Fairness-Guided Incremental Sampling (FGIS): a lightweight data intervention framework that, without access to individual sensitive attributes, generates proxy sensitive labels via Size-Aware K-Means clustering and joint MetaPath2Vec+Transformer modeling of heterogeneous mobility graphs, then enforces demographic proportionality constraints for group-aware optimization. FGIS preserves overall accuracy while reducing inter-group performance inequality by 40%, with pronounced efficacy in low-resource settings. Our key contribution is the first integration of structured demographic priors into the incremental sampling pipeline—establishing a scalable, deployable fairness-enhancement paradigm for large-scale spatiotemporal forecasting under attribute-agnostic conditions.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Bias, Fairness & Equity

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

Next location prediction underpins a growing number of mobility, retail, and public-health applications, yet its societal impacts remain largely unexplored. In this paper, we audit state-of-the-art mobility prediction models trained on a large-scale dataset, highlighting hidden disparities based on user demographics. Drawing from aggregate census data, we compute the difference in predictive performance on racial and ethnic user groups and show a systematic disparity resulting from the underlying dataset, resulting in large differences in accuracy based on location and user groups. To address this, we propose Fairness-Guided Incremental Sampling (FGIS), a group-aware sampling strategy designed for incremental data collection settings. Because individual-level demographic labels are unavailable, we introduce Size-Aware K-Means (SAKM), a clustering method that partitions users in latent mobility space while enforcing census-derived group proportions. This yields proxy racial labels for the four largest groups in the state: Asian, Black, Hispanic, and White. Built on these labels, our sampling algorithm prioritizes users based on expected performance gains and current group representation. This method incrementally constructs training datasets that reduce demographic performance gaps while preserving overall accuracy. Our method reduces total disparity between groups by up to 40% with minimal accuracy trade-offs, as evaluated on a state-of-art MetaPath2Vec model and a transformer-encoder model. Improvements are most significant in early sampling stages, highlighting the potential for fairness-aware strategies to deliver meaningful gains even in low-resource settings. Our findings expose structural inequities in mobility prediction pipelines and demonstrate how lightweight, data-centric interventions can improve fairness with little added complexity, especially for low-data applications.

Problem

• Auditing demographic disparities in mobility prediction model performance
• Addressing racial group inequity through fairness-guided sampling strategies
• Reducing accuracy gaps between demographic groups with minimal trade-offs

Innovation

• Fairness-Guided Incremental Sampling reduces demographic disparities
• Size-Aware K-Means clustering enforces census-derived group proportions
• Proxy racial labels prioritize users by performance and representation