Student Performance Analysis in Higher Education Using Integrated Approach of Machine Learning Techniques

This study investigates how machine learning (ML) methods can be used to forecast students' academic performance, assisting teachers in identifying areas of weakness and enhancing the educational process. In order to classify students' performance, the study focuses on combining clustering and classification techniques, such as fuzzy C-Means, stochastic gradient descent, support vector machines, XGBoost, gradient boosting, and K-Nearest Neighbors algorithms. The excellent accuracy of the suggested models helps administrators and teachers keep an eye on and help students achieve better results. The method allows for early intervention in learning procedures by improving prediction accuracy, especially when training datasets are available.