Examining Successful Attributes for Undergraduate Using Machine Learning Techniques

Abstract

This study utilizes both supervised and unsupervised machine learning techniques to identify the key attributes that are often demonstrated by successful learners in a computer course. Learning an introduction to computers course can be challenging for students. This study aims to explore how successful students regulate their learning in this course. By answering these questions, teachers can gain valuable insights into how students learn and which strategies are most effective for their success. To compare the accuracy, precision, and sensitivity levels of classifiers, this study employed seven supervised machine learning algorithms and ensembles. Additionally, association rule and clustering techniques were utilized to identify the key attributes for successful students. However, it is important to note that the use of a convenience sample in this study may have limited the number of students in each cluster. Key Word: Association rules, Bayesian network (BN), clustering, decision trees (DTs), K-nearest neighbour (KNN), multilayer perceptron (MLP), Naïve Bayes (NB), support vector machines (SVMs)