Is this project an undergraduate, graduate, or faculty project?
Graduate
Project Type
group
Campus
Daytona Beach
Authors' Class Standing
Elif Cankaya, Graduate Student Kyle Garber, Sophomore
Lead Presenter's Name
Elif Cankaya
Lead Presenter's College
DB College of Arts and Sciences
Faculty Mentor Name
Hong Liu
Abstract
Decision-making is one of the key activities that humans participate in. As a person develops, so does their decision-making preferences. Since choosing a major is often undergone at a young age, people often decide to switch for a more suitable major based on their current preferences. Given that major switching is common in STEM fields, and STEM’s growing importance in the modern landscape, this study aims to investigate determinants of major switching in undergraduate students. Based on our initial results, deep learning produced the best AUC, precision and recall compared to other algorithms. The confusion matrix implies that the algorithm is effective at predicting if a student will switch majors. Top correlation factors found for major switching were age, ACT scores, and GPA. Results from this study can be used to detect and predict students most likely to switch majors.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
Yes, Student Internal Grants
Predicting Undergraduate Students Major Switching
Decision-making is one of the key activities that humans participate in. As a person develops, so does their decision-making preferences. Since choosing a major is often undergone at a young age, people often decide to switch for a more suitable major based on their current preferences. Given that major switching is common in STEM fields, and STEM’s growing importance in the modern landscape, this study aims to investigate determinants of major switching in undergraduate students. Based on our initial results, deep learning produced the best AUC, precision and recall compared to other algorithms. The confusion matrix implies that the algorithm is effective at predicting if a student will switch majors. Top correlation factors found for major switching were age, ACT scores, and GPA. Results from this study can be used to detect and predict students most likely to switch majors.