PREDICTING STUDENT PERFORMANCE: A COMPARATIVE STUDY OF CLASSIFICATION ALGORITHMS USED IN MACHINE-LEARNING

Abstract

Education is a deliberate action with certain goals in mind, such as passing on knowledge or developing skills and character qualities. Education is also seen as a crucial prerequisite for boosting self-confidence and giving people the tools they need to take part in the rapidly changing world of today. We can measure the growth of the educational institution using the students' progress. Analysing student academic performance is essential for academic institutions and educators to decide how to enhance individual student performance. Finding meaningful patterns in a lot of data is what machine learning is all about. Machine learning is quickly becoming recognized as a promising framework that offers a large range of tools, strategies, and procedures that make it possible to thoroughly analyse the data that is currently available in many sectors. Machine-learning techniques are helpful for improving the present educational standards and academic management in education. These techniques provide a route to various degrees of ranking, which is a discovery that alters how people view how to excel in the educational field. This research introduces a paradigm for predicting students' academic progress using machine learning (ML) algorithms. Through the use of several machine learning (ML) algorithms, this initiative analyses historical student outcomes and their unique traits, including family history, demographic distribution, age, and study attitude.