Systematic Analysis of Datamining Methods in Education

Abstract Educational Data Mining (EDM) is a rapidly expanding discipline focused on exploring data generated within educational settings. This paper conducts a systematic analysis of the EDM research literature to: (a) investigate the data mining methods used in academia and non-academic institutions; (b) review and compare these methods; and (c) classify them to understand their potential for solving educational issues. Based on a structured review of key EDM journals and conferences, the study categorizes common methods into major groups, including classification (e.g., C4.5, CHAID), clustering (e.g., K-means), association rule learning, and regression analysis. The paper also examines the primary data sources (e.g., Learning Management Systems, Student Information Systems) and essential data preprocessing techniques (e.g., data cleaning, transformation, reduction). Key applications are explored through case studies, such as predicting student performance and identifying at-risk students. Finally, the analysis addresses significant challenges (e.g., data privacy, data quality, algorithmic bias, scalability) and outlines future directions, including the integration of AI, real-time data analysis, and the development of personalized learning experiences. Keywords: Educational Data Mining (EDM), Systematic Analysis, Machine Learning, Classification, Clustering, Regression, Student Performance Prediction, At-Risk Students, Data Privacy, Algorithmic Bias, Personalized Learning.