Predicting Nursing Graduates Using Machine Learning Models

• Activity Number: 132 - SLDS CSpeed 1
• Type: Contributed
• Date/Time: Monday, August 9, 2021 : 1:30 PM to 3:20 PM
• Sponsor: Section on Statistical Learning and Data Science
• Author(s): Xiaoyue Cheng* and Li Hannaford and Mary Kunes-Connell
• Companies: University of Nebraska at Omaha and Creighton University and Creighton University
• Keywords: machine learning; graduation rate; dropout risk; education data

Abstract

To improve the graduation rate of nursing baccalaureate program, this study aims to identify students at-risk at an earlier stage before they withdraw from the program. Data from 773 students are collected from a nursing baccalaureate program. Student-level information including demographic background, high school level, and college academic performance was employed to predict whether students will graduate within six years. Predictions were made at five time points: the beginning of the first, second, third, fourth years, and the end of the sixth year. A set of machine learning methods were applied and compared at each time point. The results suggest that random forest and the stacked model outperform other methods. The prediction accuracy improves over time. Among all the variables, cumulative grade points average (GPA) and nursing course GPA are the most influential factors for predicting graduation. The application of our models can help nurse educators identify the at-risk students early on and provide personalized assistance to maximize graduation rate.