Machine Learning-Driven Predictions to Enhance Academic Performance in High School Students: Systematic Literature Review

This research aims to enhance students' learning effectiveness through the application of existing Machine Learning techniques. By reviewing various studies in this field, the research explores the implementation of machine learning to develop effective intervention strategies for improving student academic performance. Utilizing machine learning, individualized education paths derived from student-specific factors such as past performance data and learning styles are implemented to maximize student progress. To predict students' academic performance, a variety of machine learning algorithms are employed, including Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Decision Trees, Naive Bayes, and Artificial Neural Networks (ANN), as well as models like Linear Regression. The selection of these methods is based on the data features, dataset size, and the specific prediction goals. Additionally, prediction accuracy can be enhanced by combining these methods or integrating them with deep learning approaches. As machine learning integration in classrooms becomes increasingly essential, this paper examines the literature on the use of these algorithms in education, highlighting significant findings and analyzing their potential impact on personalized and adaptive learning environments. In conclusion, the research demonstrates that machine learning can significantly optimize and enhance academic performance, particularly in high school students.