Finding Bottlenecks: Predicting Student Attrition with Unsupervised Classifier

摘要

With pressure to increase graduation rates and reduce time to degree inhigher education, it is important to identify at-risk students early. Automatedearly warning systems are therefore highly desirable. In this paper, we useunsupervised clustering techniques to predict the graduation status of declaredmajors in five departments at California State University Northridge (CSUN),based on a minimal number of lower division courses in each major. In addition,we use the detected clusters to identify hidden bottleneck courses.