How Well a Student Performed? A Machine Learning Approach to Classify Students’ Performance on Virtual Learning Environment

Prediction of student's performance using different relevant information has emerged as an efficient tool in educational institutes towards improving the curriculum and teaching methodologies. Automated analysis of educational data using state of the art Machine Learning (ML) and Artificial Intelligence (AI) algorithms is an active area of research. The research addresses the problem of student performance prediction by using three ML algorithms (i.e., Support Vector Classifier (SVC), k-Nearest Neighbour (k-NN), Artificial Neural Network (ANN)) on Open University (OU) dataset. Educational data is analyzed for three main indicators including demographic, engagement and performance. From the experimental analysis, the k-NN approach emerged as best for OU experiments when compared among applied and with existing literature. Improvement of results is attributed to change in dealing with missing values and data standardization approaches.