Machine Learning Strategy for Enhancing Academic Achievement in Private University

Learning analytics has developed into a powerful tool for discovering unforeseen patterns in educational data and forecasting students' academic success. In order to anticipate the final exam grades of students studying software engineering, this study suggests a learning analytics framework based on machine learning algorithms, using component grades as the source data. The dataset included the academic performance grades of 1475 students who enrolled in a private university for a year to take a Java Web Programming course. To estimate the students' final test grades, the Naive Bayes and Decision Tree algorithms' performances―which are among the machine learning algorithms were calculated and compared. A multitude of features, including the assignment, practical exam, two progress test, two workshop, and final exam, were used to make the predictions. Such data-driven research is crucial for developing a framework for learning analytics in higher education and for influencing decision-making.