Predicting Dropout for Nontraditional College Students: A Machine Learning Approach

• In Event: Student Persistence

Abstract

Student attrition represents one of the greatest challenges facing U.S. postsecondary institutions. The majority of students who seek a bachelor’s degree do not graduate within 6 years; among nontraditional students, who make up half of the postsecondary population, dropout rates are even higher. In this study, we developed a machine learning classifier using the XGBoost model and NCES BPS:12/14 data to predict nontraditional student dropout. In comparison with standard logistic regression models, XGBoost displayed superior performance in predicting dropout. The predictive ability of the model and the features it identified as being most important in predicting nontraditional-student dropout can inform discussion among educators seeking ways to identify and support at-risk students early in their postsecondary careers.

Authors

• Huade Huo, American Institutes for Research

• jiashan Cui, American Institutes for Research

• Mark Ossolinski, American Institutes for Research

• Sarah Marie Hein, American Institutes for Research

• Zoe Padgett, American Institutes for Research

• Ruth Raim, American Institutes for Research

• Jijun Zhang, American Institutes for Research