Application of data mining techniques in an educational background can recognize hidden knowledge and patterns that will assist in decision-making procedure for improving educational system. In e-learning system or web-based education, student’s academic performance features play an important role that will show the student’s interactivity towards the e-learning system. The aim of this paper is to show the importance of features and for this task we have collected the educational dataset from real time database and online EDM database. On the included dataset, feature analysis has been done and after that, data pre-processing phase that is an important step in knowledge discovery process is cast off in this work. On pre-processed dataset, classification is performed using classifiers namely; Decision Tree (ID3), Nave Bayes, K-Nearest Neighbour, Support vector machines to predict student’s academic performance along with the efficient Ant colony optimization technique. The accuracy of the proposed model is 85.61% achieved by using Ensemble Methods. Here, bagging, boosting, voting, validation and optimization are combined ensemble methods used. On using ensemble methods, better result has been acquired that proves reliability of anticipated model. Performance metrics such as accuracy, precision, recall, T measure, F-measure, P-value are computed here. Simulation was carried out in MATLAB environment.
Volume 11 | 06-Special Issue
Pages: 1660-1671