Predict Student Performance with Machine Learning method: A - Review

In educational institutions, a significant amount of effort and important resources are allocated to influence, predict, and understand students' decisions when choosing their educational paths. Leveraging student data and achievements with the assistance of machine learning to predict students' academic success can make a substantial contribution to all parties involved in devising appropriate strategies to support students. This review assesses the performance of machine learning algorithms in classifying and predicting student academic success. Four algorithms are considered for predicting student academic success: K-Nearest Neighbors (KNN), Naïve Bayes, Logistic Regression, Support Vector Machine (SVM), and Decision Tree. Additionally, this review utilizes data that categorizes students' academic success into two or three categories, such as pass/fail or fail/pass/excellent.