Utilizing learning analytics to analyze and predict student academic performance

Résumé

This study seeks to evaluate students' academic performance across various subjects, identify disparities in educational outcomes, and explore the individual, familial, institutional, and socio-economic factors that influence these performances. By doing so, it aims to provide a comprehensive understanding of the dynamics affecting student achievement. Data were gathered from the ELMOSSALA school within the provincial directorate of Meknes for the year 2024. The analysis involved examining exam results to evaluate students' mastery of fundamental skills in each subject area. Statistical tests were utilized to compare performance across different subjects. Additionally, multiple regression analysis was conducted to identify influential factors, and advanced data analysis techniques were employed to uncover predictive characteristics linked to academic success. Various machine learning algorithms were also assessed for their efficacy in predicting student performance. The results revealed notable variations in student performance across subject areas, with significant disparities observed between them. Key factors impacting academic performance included socio-economic status, the quality of teaching, and individual student characteristics. Furthermore, some machine learning algorithms demonstrated greater effectiveness than others in predicting learners' performance, highlighting the potential of these technologies in educational settings. While this study provides valuable insights, it is important to acknowledge certain limitations. The research is based on data from a single school, which may limit the generalizability of the findings to broader educational contexts. Additionally, the study focuses primarily on quantitative measures, potentially overlooking qualitative aspects that could further enrich the understanding of student performance.

Classification JEL : C80

Paper type : Empirical Research