Prediction and assessment of student learning outcomes in calculus a decision support of integrating data mining and Bayesian belief networks

A decision support system based on data mining (DM) and Bayesian belief networks (BBN) is proposed to predict the student learning outcomes and takes the calculus course as an example to help students overcome their learning difficulties. Total of 427 freshmen in Ming Chi University of Technology (Taiwan) did questionnaires to assist this study. The methodologies involves four steps: fuzzy theory to identify the factors on learning outcomes; data mining to construct influence diagram; machine learning to establish the probability tables in BBN; and the model to predict the exam scores at the beginning of course and thereby to help students enhance their scores according to their weakness.