Scholarlink

In the context of secondary education, anticipating students’ academic success is a major challenge for improving educational support and guidance. This study proposes a predictive approach based on the Random Forest algorithm, known for its ability to handle complex data while maintaining good interpretability. The model was trained using academic data collected over four years from students in the Greater Casablanca region of Morocco. It predicts performance in four major tracks of the Moroccan baccalaureate: Mathematical Sciences, Physical Sciences, Life and Earth Sciences, and Economics. To highlight the practical value of the model, a prototype platform named MyStudyPath was developed. It provides a decision-support tool designed for students, teachers, and academic advisors. This work contributes to the field of educational technology and underscores the potential of machine learning approaches in guiding academic pathways.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Forecasting Academic Success in Moroccan Secondary Education: Development of a Predictive Tool Based on Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Salma Sammah,
  • Mohammed Ait Daoud,
  • Khadija Achtaich,
  • Abderrahim Tragha

摘要

In the context of secondary education, anticipating students’ academic success is a major challenge for improving educational support and guidance. This study proposes a predictive approach based on the Random Forest algorithm, known for its ability to handle complex data while maintaining good interpretability. The model was trained using academic data collected over four years from students in the Greater Casablanca region of Morocco. It predicts performance in four major tracks of the Moroccan baccalaureate: Mathematical Sciences, Physical Sciences, Life and Earth Sciences, and Economics. To highlight the practical value of the model, a prototype platform named MyStudyPath was developed. It provides a decision-support tool designed for students, teachers, and academic advisors. This work contributes to the field of educational technology and underscores the potential of machine learning approaches in guiding academic pathways.