Rethnicity: Predicting Ethnicity from Names

TL;DR

This paper introduces an R package called 'rethnicity' that predicts ethnicity from names using a Bidirectional LSTM model trained on Florida Voter Registration data, emphasizing minority group accuracy and integration with R.

Contribution

The paper presents a new R package for ethnicity prediction from names, utilizing deep learning and addressing minority group accuracy, with integration into R and performance comparison.

Findings

High accuracy in ethnicity prediction, especially for minority groups

Effective integration of deep learning model with R via Rcpp

Competitive performance compared to existing solutions

Abstract

In this study, a new R package, \texttt{rethnicity} is provided for predicting ethnicity based on names. The Bidirectional LSTM and Florida Voter Registration were used as the model and training data, respectively. Special care was given for the accuracy of minority groups, by adjusting the imbalance in the dataset. The models were trained and exported to C++ and then integrated with R using Rcpp. Additionally, the availability, accuracy, and performance of the package were compared with other solutions.