2026 ASEE Annual Conference & Exposition

Leveraging Machine Learning Techniques to Evaluate Persistence in Engineering

Presented at Student Division (STDT) Technical Session 1

Understanding students’ persistence through college is a valuable resource for creating possible interventions to increase retention, especially in engineering, where attrition rates are high. While much research has been conducted about persistence and graduation in engineering, less is known about how the influences on persistence vary from year to year. By determining which factors have the strongest correlation with persistence to graduation and the next academic year, we can predict student success at several key academic milestones. This research utilized the MIDFIELD (Multiple Institution Database for Investigating Engineering Longitudinal Development) dataset, employing machine learning methods to identify the factors that best predict graduation and persistence in the following year. Persistence in the university, engineering program, and degree program was observed. The study also tracked how the predictive power of different variables changed over time. Our results suggest that factors directly affected by a student’s decisions in college were stronger predictors of persistence than factors determined before college or demographic characteristics. These “environment variables” remained strong predictors for the first six years of undergraduate study that were analyzed. We hope that future research can uncover the extent to which these factors can predict persistence in engineering.

Authors

Alexa Catherine Andershock The University of Tennessee, Knoxville [biography]

Lexy Andershock is an incoming Engineering Education Ph.D. student at Virginia Tech. Her research interests include the influence of first-year engineering programs on engineering students, especially relating to major choice and future academic performance. She earned her B.S. in Computer Science from the University of Tennessee, Knoxville.
Baker A. Martin http://orcid.org/0000-0003-3437-9293 University of Tennessee at Knoxville [biography]

Baker Martin is a Teaching Assistant Professor in Engineering Fundamentals at the University of Tennessee, Knoxville, where he teaches in the first-year engineering program. His research interests include choice and decision making, especially relating to first-year engineering students’ major selection. He earned his Ph.D. in Engineering and Science Education from Clemson University, his M.S. in Chemical Engineering from the University of Tennessee, Knoxville, and his B.S. in Chemical Engineering from Virginia Tech.
Rachael Bevill Burns University of Tennessee at Knoxville [biography]

Rachael Bevill Burns is an Assistant Professor of Electrical Engineering and Computer Science at the University of Tennessee, Knoxville. She earned her Ph.D. in Computer Science from the Max Planck Institute for Intelligent Systems (MPI-IS) in Stuttgart, Germany, and her B.S. and M.S. in Biomedical Engineering from the George Washington University in Washington, D.C. Her research lab, STARI, is one of five Max Planck Partner Groups in the US, a prestigious affiliation with the Max Planck Society in Germany promoting cutting-edge, collaborative international research.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session