Prediction of Student Success Through Analysis of Moodle Logs: Case Study

Abstract

Data mining together with learning analytics are emerging topics because of the huge amount of educational data coming from learning management systems. This paper presents a case study about students’ grade prediction by using data mining methods. Data obtained from Moodle log files are explored to understand the trends and effects of students’ activities on Moodle learning management system. Correlations of system activities with the student success are found. Data is classified and modeled by using decision tree, Bayesian Network and Support Vector Machine algorithms. After training the model with a one-year course activity data, next years’ grades are predicted. We found that Decision tree classification gives the best accuracy on the test data for the prediction.