EVALUATION OF PREDICTIVE DATA MINING ALGORITHMS IN STUDENT ACADEMIC PERFORMANCE

Based on the analysis of different metrics, this research identifies the most performing predictive algorithms in educational data environment using the Faculty Support System (FSS) model, and provides a summary of current practice and guidance on how to evaluate educational models. The study uses Naive Bayes, Multilayer Perceptron, Random Forests and J48 decision tree induction to build predictive data mining models on 111 instances of students' data. We applied 10-fold cross-validation, percentage split and training set methods on data and performance metrics were used to evaluate the baseline predictive performance of the classifiers. The comparative analysis indications that the Multilayer Perceptron performed best with accuracy of 82% and Random Forests came out second with accuracy of 79%, J48 and Naive Bayes came out the worst with accuracy of around 60%. The evaluation of these classifiers on educational datasets, gave an insight into how different data mining algorithms predict student performance and enhance student retention.