A data mining approach using machine learning algorithms for early detection of low-performing students
Ean Teng Khor
Abstract
Purpose The purpose of the study is to build predictive models for early detection of low-performing students and examine the factors that influence massive open online courses students' performance. Design/methodology/approach For the first step, the author performed exploratory data analysis to analyze the dataset. The process was then followed by data pre-processing and feature engineering (Step 2). Next, the author conducted data modelling and prediction (Step 3). Finally, the performance of the developed models was evaluated (Step 4). Findings The paper found that the decision trees algorithm outperformed other machine learning algorithms. The study also confirms the significant effect of the academic background and virtual learning environment (VLE) interactions feature categories to academic performance. The accuracy enhancement is 17.66% for decision trees classifier, 3.49% for logistic regression classifier and 4.89% for neural networks classifier. Based on the results of CorrelationAttributeEval technique with the use of a ranker search method, the author found that the assessment_score and sum_click features are more important among academic background and VLE interactions feature categories for the classification analysis in predicting students' academic performance. Originality/value The work meets the originality requirement.