Predicting Academic Success: A Comparative Study of Machine Learning and Clustering-Based Subject Recommendation Models

Abstract

The study of students' academic performance is a significant endeavor for higher education schools and universities since it is essential to the design and management of instructional strategies. The efficacy of the current educational system must be monitored by evaluating student achievement. For this research, we used multiple Machine Learning algorithms and Neural Networks to analyze the learning quality. This study investigates the real results of university examinations for B.Tech (Bachelor in Technology) students, a four-year undergraduate programme in Computer Science and Technology. The K-means clustering approach is used to recommend courses, highlighting those that would challenge students and those that will improve their GPA. The Linear Regression method is used to make a prediction of a student’s rank among their batchmates. Academic planners might base operational choices and future planning on the findings of this study.