Nombre de la producción

Predicting High School Students' Academic Performance_ A Comparative Study Of Supervised Machine Learning Techniques _ Ieee Conference Publication _ Ieee Xplore

Tipología de la producción

Productos Resultados de Actividades de Generación de Nuevo Conocimiento

Fecha de publicación del producto

06/03/2025

Descripción de la producción

The proliferation of mobile devices and the rapid development of information and communication technologies have revolutionized education. Educational data has evolved to be voluminously massive, broadly various, and produced at high velocity. Therefore, computerized techniques for integrating, processing, and transforming data into valuable knowledge have become necessary to improve internal academic processes. Specifically, educational data mining is an emerging discipline concerned with analyzing the massive amounts of academic data generated and stored by educational institutions. In this sense, machine learning algorithms aid decision-makers who are establishing strategies to improve students' learning experience and institutional effectiveness by revealing hidden patterns in academic performance. Thus, this paper describes our comparative study of machine learning techniques to predict academic performance. We selected the features that best fit the discovery of patterns in the academic performance of high school students, resulting in a balance between accuracy and interpretability. We implemented six supervised learning algorithms for pattern recognition: Light Gradient Boosting Machine, Gradient Boosting, AdaBoost, Logistic Regression, Random Forest, and K-nearest Neighbors. The experimental results showed that the Gradient Boosting (Gbc) algorithm achieved the highest accuracy (96.77%), superior to other classification techniques considered.

Clasificación Internacional Normalizada de la Educación (CINE)

Tecnologías de la Información y la Comunicación (TIC)