Predicting Students' Performance in Distance Learning Using Machine Learning Techniques

Abstract

The ability to predict a student's performance could be useful in a great number of different ways associated with university-level distance learning. Students' key demographic characteristics and their marks on a few written assignments can constitute the training set for a supervised machine learning algorithm. The learning algorithm could then be able to predict the performance of new students, thus becoming a useful tool for identifying predicted poor performers. The scope of this work is to compare some of the state of the art learning algorithms. Two experiments have been conducted with six algorithms, which were trained using data sets provided by the Hellenic Open University. Among other significant conclusions, it was found that the Naïve Bayes algorithm is the most appropriate to be used for the construction of a software support tool, has more than satisfactory accuracy, its overall sensitivity is extremely satisfactory, and is the easiest algorithm to implement.Computers do not learn as well as people do, but many machine-learning algorithms have been found that are effective for some types of learning tasks. They are especially useful in poorly understood domains where humans might not have the knowledge needed to develop effective knowledge-engineering algorithms. Generally, machine learning (ML) explores

Brief Review of Educational Applications Using Data Mining and Machine Learning

“…On the other hand, campus services and facilities had less effect on their satisfaction. Kotsiantis, Pierrakeas and Pintelas (2004) performed two experiments to predict new students' performance in computer engineering in the Hellenic Open University, Greece. They experimented using six algorithms: decision trees, neural networks, naive Bayes, k-nearest neighbors, logistic regression and support vector machines.…”

Comparative Study: Feature Selection Methods in the Blended Learning Environment

“…For creating a model of prediction algorithms of Regression Trees (CART) and CHAID classification were used. Authors [39] use set of method of features selection for extraction of the subset of input variables. On the extracted set, the following classification algorithms were used: Decision tree, Perception-based Learning, Bayesian Nets, Instance-Based Learning and Rule learning for prediction of student' performances on e-learning module.…”

Early Prediction of Students Performance using Machine Learning Techniques

“…Choice of algorithm is critical because the accuracy of prediction is often dependent on these algorithms. Over the years several researchers [3,4,5,6,7,8,9] have used varied MLAs to perform classification in various knowledge domain. In this study five classes of MLAs has been chosen for classification with a representative algorithm from each class.…”

“…Kotsiantis et al [4] described a model to predict student results for a distance learning course in Hellenic Open University. Predictions were done on the basis of marks obtained in written assignments.…”