PREDICTING STUDENT PERFORMANCE WITH DATA MINING AND LEARNING ANALYTICS TECHNIQUES: A SYSTEMATIC LITERATURE REVIEW
This article presents a systematic literature review of studies that have used data mining and learning analytics techniques to predict student performance. The review covers a period of 10 years (2011-2021) and examines a total of 50 papers from various sources. The results show that data mining and learning analytics techniques have been widely used to predict student performance in different educational contexts, including K-12, higher education, and online learning. The most commonly used data mining and learning analytics techniques were decision trees, logistic regression, neural networks, and support vector machines. The review identifies the main challenges and limitations of using data mining and learning analytics techniques for predicting student performance, including issues related to data quality, feature selection, model validation, and ethical considerations. The article concludes with recommendations for future research in this area.