Using Data Mining to Model Student Success

Abstract

As funding for higher education through federal and state sources continues to decline, and a stronger call for accountability is placed upon higher education institutions to graduate students within the expected amount of time, colleges and universities are looking for ways to best leverage their resources to attract college-ready students who will enroll in their institutions, remain enrolled consistently, and earn their undergraduate degrees in a timely manner. Federal research conducted by the U.S. Department of Education's National Center for Education Statistics through the Integrated Postsecondary Education Data System (IPEDS) examines aggregate student enrollment, degree completions, and graduation rates. But to be truly helpful to the institutional researcher, unit record data is required. Only by examining the many attributes of each individual student can an institution determine the unique characteristics which will lead to student academic success -- degree attainment. Because of the overall readability and the strong level of accuracy they can produce, decision trees are a good method for identifying the relationships between attributes in large datasets. Therefore, this study explores the use of data mining on higher education unit record data to develop a decision tree classification model of student success..