Smart Education Through Data Analytics

Educational data mining applies data analysis techniques to understand past trends and predict future academic outcomes.Higher education institutions collect extensive data on students and faculty, which can be effectively utilized to analyze and predict academic performance.This study explores the use of data mining methods in the educational domain to evaluate students' and teachers' performance.Student achievement is classified into categories such as Excellent, Good, Average, and Poor/Fail.The K-means clustering algorithm is employed using attributes including attendance, sessional marks, and assignment scores.Additionally, a Rule-Based Classification approach is used to extract meaningful relationships between data attributes and performance classes.The study highlights the potential of data mining techniques in supporting academic decision-making at the university and college levels.