Can We Trust Race Prediction?

Cangyuan Li
7/17/2023
cs.LGcs.AIcs.CY

Official code: CangyuanLi/pyethnicity (4 stars, MIT, last commit 2025-08-23).

Abstract

In the absence of sensitive race and ethnicity data, researchers, regulators, and firms alike turn to proxies. In this paper, I train a Bidirectional Long Short-Term Memory (BiLSTM) model on a novel dataset of voter registration data from all 50 US states and create an ensemble that achieves up to 36.8% higher out of sample (OOS) F1 scores than the best performing machine learning models in the literature. Additionally, I construct the most comprehensive database of first and surname distributions in the US in order to improve the coverage and accuracy of Bayesian Improved Surname Geocoding (BISG) and Bayesian Improved Firstname Surname Geocoding (BIFSG). Finally, I provide the first high-quality benchmark dataset in order to fairly compare existing models and aid future model developers.

View on arXivView PDF

Code Implementations(1)

CangyuanLi/pyethnicityOfficial100%
MIT

Predict race from name and location

43R, StataJul 22, 20231 years agoMIT
deep-learningrace-prediction

Similar Papers

LSTM+Geo with xgBoost Filtering: A Novel Approach for Race and Ethnicity Imputation with Reduced Bias

86% match2025

Nationality and Region Prediction from Names: A Comparative Study of Neural Models and Large Language Models

79% match2026

Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models

78% match2024

SR4-Fit: An Interpretable and Informative Classification Algorithm Applied to Prediction of U.S. House of Representatives Elections

77% match2026

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

77% match2025

An Investigation Into Race Bias in Random Forest Models Based on Breast DCE-MRI Derived Radiomics Features

77% match2023

Cite this paper

@article{li2023trust,
  title  = {Can We Trust Race Prediction?},
  author = {Cangyuan Li},
  year   = {2023},
  eprint = {2307.08496},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.08496v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.08496.svg)](https://codeofpaper.com/paper/2307.08496)

Discussion