Data Mining Techniques Based Students Achievements Analysis

Abstract

In this work, data mining techniques are used to determine the students’ achievements in Mathematic class. In other words, we use the data mining techniques to determine if there is any link between the student achievement and various student related data such as student grades, demographic, social information and school related data. Data mining techniques, Decision Tree (DT), Discriminant Analysis (DA), Support Vector Machines (SVM), k-nearest neighbor (K-NN) and ensemble learner are used in prediction purposes. A publicly available dataset is considered in experimental works. Experimental works, on computer environment are carried out to validate the data mining techniques. All data mining methodologies are simulated on MATLAB environment with 5-fold cross-validation technique. The classification performance is measured by accuracy and root mean square error (RMSE) criterions. Three experimental setups and for each setup, three scenarios are considered during experimentation. The obtained results are encouraging and the comparison with some of the existing achievements shows the superiority of our work.