Predictive Analysis of Student Performance using Machine Learning Models
Year: 2025
Type: article
Abstract: In order to recognize the students who are not performing well, it is of great significance to predict student performance with the highest accuracy possible. In this study, the functions of machine learning techniques, such as Random Forest, Gradient Boosting, XGBoost, and Support Vector Classifier are employed in the prediction of student outcomes depending on studied hours, attendance, activities, and parental education level. Accordingly, after the dataset was pre-processed and the models were assessed using the machine learning models, the Gradient Boosting gave the best accuracy output measuring 97% while the Random Forest was remarkably close, producing almost identical results in terms of accuracy. The effectiveness of drawing on data to identify students who are at high risk of dropping out of an institution is brought out in this study.
Authors: Aarti Rathod, Neha Vora
Institution: Shri Vile Parle Kelavani Mandal
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W4409144338