Early Detection of Students at Risk - Predicting Student Dropouts Using Administrative Student Data from German Universities and Machine Learning Methods

Abstract

To successfully reduce student attrition, it is imperative to understand what the underlying determinants of attrition are and which students are at risk of dropping out. We develop an early detection system (EDS) using administrative student data from a state and private university to predict student dropout as a basis for a targeted intervention. To create an EDS that can be used in any German university, we use the AdaBoost Algorithm to combine regression analysis, neural networks, and decision trees - instead of relying on only one specific method. Prediction accuracy at the end of the first semester is 79% for the state university and 85% for the private university of applied sciences. After the fourth semester, the accuracy improves to 90% for the state university and 95% for the private university of applied sciences.