Understanding how these conditions impact students is important given the expense of a degree in America. This study presents data for 160,933 students attending a large American research university.
Using a machine learning technique called gradient boosting we present time-to-graduation predictive models trained on data that includes academic performance, enrollment, demographics, and features regarding a student's preparation for university.
We demonstrate that enrollment factors (such as changing a major) lead to greater increases in model predictive performance of when a student graduates than performance factors (such as grades) or preparation (such as high school GPA).