Abstract

This study examines how race, experience, and industry shape callback rates in hiring using the ResumeNames dataset of 4,066 fictitious resumes. Logistic regression and decision tree models reveal that race is the strongest predictor of callbacks: White-sounding names received more responses than Black-sounding names, even with equal or stronger qualifications. Black applicants needed significantly more experience to match the success rates of White applicants. Transport and Communication was the only industry where Black applicants saw higher callback rates, likely due to its historical ties to back-facing labor roles. Exploratory analysis also suggested a racial double standard in how resume quality and employment gaps are evaluated. The findings show the need for further research into how bias, algorithms, quality, and experience alignment intersect in hiring.

Advisor

Long, Colby

Department

Statistical and Data Sciences

Disciplines

Data Science

Keywords

Resumes, Resume names, Hiring bias, Discrimination, African-American, Black

Publication Date

2025

Degree Granted

Bachelor of Arts

Document Type

Senior Independent Study Thesis

Share

COinS
 

© Copyright 2025 Kayla Robinson