A Decision Tree Approach to Predictive Modeling of Student Performance in Engineering Dynamics

A decision tree model has been developed to predict student performance in Engineering Dynamics based on 750 data records collected from 125 students in two semesters. The predictor variables include a student's cumulative GPA and scores in four prerequisite courses: Engineering Statics, Calculus I, Calculus II, and Physics. The model generates nine decision rules and shows that a student's performance in Statics and cumulative GPA play the two most significant roles in governing the student's performance in Dynamics. The prediction accuracy of the model is more than 80%, which is at least 14% higher than that of the traditional multivariate regression model.