Nowadays, Educational Data Mining (EDM), begun as a new research area due to the broadening of numerous statistical approaches that are used to perform data exploration in educational settings. One of the applications of EDM is the prediction of performance of students. In a web based education system, the behavioural features of learners are very significant in showing the interaction between students and the LMS. In this paper, our aim is to propose a new performance prediction model for students which is based on data mining methods which includes new features known as behavioural features of students and based on sequential feature selection which is used to identify most important features. The proposed performance model is evaluated using classifiers such as Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Decision Tree (DT). Furthermore, so as to enhance the classifiers performance, the ensemble methods such as Bagging, Boosting and Random Forest were applied. The achieved results show that there exists a strong relationship between behaviour of students and their academic performance. An accuracy of 91.5% was gotten when the ensemble methods were applied to the classifiers to improve the academic performance. Thus, the result gotten shows the reliability of the proposed model.
Paper
Full text
Educational Data Mining: Enhancement of Student Performance model using Ensemble Methods
Semantic Scholar · Computer Science · 2019
Abstract
Nowadays, Educational Data Mining (EDM), begun as a new research area due to the broadening of numerous statistical approaches that are used to perform data exploration in educational settings. One of the applications of EDM is the prediction of performance of students. In a web based education system, the behavioural features of learners are very significant in showing the interaction between students and the LMS. In this paper, our aim is to propose a new performance prediction model for students which is based on data mining methods which includes new features known as behavioural features of students and based on sequential feature selection which is used to identify most important features. The proposed performance model is evaluated using classifiers such as Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Decision Tree (DT). Furthermore, so as to enhance the classifiers performance, the ensemble methods such as Bagging, Boosting and Random Forest were applied. The achieved results show that there exists a strong relationship between behaviour of students and their academic performance. An accuracy of 91.5% was gotten when the ensemble methods were applied to the classifiers to improve the academic performance. Thus, the result gotten shows the reliability of the proposed model.