Improving Student Retention by Predicting Scholarship Renewal Eligibility with Machine Learning
dc.contributor.advisor | Affonso, Lancie A | |
dc.contributor.author | Schaich, Mackenzie Jordan | |
dc.date.accessioned | 2022-03-25T17:38:36Z | |
dc.date.available | 2022-03-25T17:38:36Z | |
dc.date.created | 2019-05 | |
dc.date.submitted | May 2019 | |
dc.description.abstract | South Carolina awards the Legislative Incentive for Future Excellence (LIFE) scholarship of up to $5000 to residents attending a public university who achieve two of three criteria based on high school GPA, ACT/SAT score, and class rank. Between 600 and 800 LIFE scholars enroll at College of Charleston annually. However, by the end of their freshman year, 47% of scholars fail to meet the renewal requirements. Of those who are ineligible for renewal, 45% fail to return to CofC the following semester. Identifying students who are at-risk of losing their LIFE scholarship is advantageous to both individual students and the institution. The statistical models trained for this project can accurately identify 76% of students will become ineligible to renew their scholarships based on data known at the time of class enrollment. In addition, we can group the students into different risk profiles so that targeted intervention can be undertaken to prevent students from losing eligibility. | |
dc.format.mimetype | application/pdf | |
dc.identifier.uri | https://repository.library.cofc.edu/handle/123456789/5280 | |
dc.language.iso | en_US | |
dc.subject | predictive analytics, student retention, six-year graduation rate, random forest | |
dc.title | Improving Student Retention by Predicting Scholarship Renewal Eligibility with Machine Learning | |
dc.type.genre | thesis | |
dc.type.material | text | |
thesis.additionaldegree.discipline | Economics | |
thesis.degree.department | Computer Science | |
thesis.degree.discipline | Data Science | |
thesis.degree.grantor | College of Charleston | |
thesis.degree.name | Bachelor of Science |