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

作者：Fang, Ning^*; Lu, Jingui

来源：International Journal of Engineering Education, 2010, 26(1): 87-95.

• decision trees
• predictive modeling
• multivariate regression
• 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.

• 出版日期2010
• 单位南京工业大学