Spatial Fairness

Description

Due to certain historical practices like redlining, location data (especially zip codes) within the United States can be correlated with demographic information such as race and/or ethnicity. In certain domains (e.g., in hiring or the lending industry), such demographic traits may be considered protected by law. With spatial fairness, we aim to ensure no discrimination occurs with respect to these legally protected attributes in decision-making scenarios where location is central to the task at hand.


  • Nripsuta Ani Saxena, Wenbin Zhang, and Cyrus Shahabi. Unveiling and mitigating bias in ride-hailing pricing for equitable policy making., AI and Ethics (2024): 1-12.

  • Nripsuta Ani Saxena, Wenbin Zhang, and Cyrus Shahabi. Missed Opportunities in Fair AI. Proceedings of the 2023 SIAM International Conference on Data Mining (SDM) . Society for Industrial and Applied Mathematics, 2023.


People


Nripsuta (Ani) Saxena

CS PhD Student, USC