An Artificial Neural Network for Predicting Student Graduation Outcomes

Declining student graduation rates is a significant and growing problem in higher education. Students are dropping out from colleges for a variety of reasons and school administrators are scrambling to increase graduation rates. Predicting student graduation is of great value to schools and an enormous potential utility for targeted intervention. Considering the promising behavior of Artificial Neural Networks (ANNs) as classifiers led us into the development, training, and testing of an ANN for predicting student graduation outcomes. The network was developed as a three-layered perceptron and was trained using the backpropagation principles. For training and testing various experiments were executed. In these experiments, a sample of 1,407 profiles of students was used. The sample represented students at Waubonsee College and it was divided into two sets. The first set of 1,100 profiles was used for training and the remaining 307 profiles were used for testing. The average predictability rate for the training and test sets were 77% and 68%, respectively.