Using Decision Trees to Understand Student Data

We apply and evaluate a decision tree al-gorithm to university records, producing human-readable graphs that are useful both for predicting graduation, and understanding factors that lead to graduation. We compare this method to that of nueral networks, Sup-port Vector Machines, and Kernel Regres-sion, and show that it is equally powerful as a classificaion tool. At the same time, decision trees provide simple, readable models of graduation that we hope decision-makers will find useful in assessing their programs and understanding their student body. 1