Scholarlink

In the context of increasingly heterogeneous student populations and a growing emphasis on data-driven decision-making, accurately predicting academic performance remains a m193 ajor challenge. This study investigates the use of regression-based machine learning models to estimate continuous academic outcomes, specifically the final average scores of adolescent students (Patil et al., in Int J Comput Appl 176(22):15–21, 2024, [1]). Data were collected from Moroccan schools using a cluster sampling strategy, following a methodology inspired by prior educational research (Romero et al., in IEEE Transactions on Systems, Man, and Cybernetics, Part C, vol 40, no 6, pp 601–618 (2010), [2]). Several supervised learning algorithms including Linear Regression, Random Forest Regressor, Decision Tree Regressor, and K-Nearest Neighbors Regressor were trained and evaluated using a standard train-test split. Model performance was assessed with standard regression metrics: coefficient of determination ( \(R^2\) ), mean absolute error (MAE), and mean absolute percentage error (MAPE). The ultimate goal is to develop a reliable system that supports the early identification of at-risk students and informs personalized pedagogical interventions. Findings highlight the practical relevance of machine learning in improving academic guidance and individualized learning strategies.

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

Predicting Academic Performance Using Machine Learning: Moroccan Middle School Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nouhaila Ben El Khadra,
  • Ibtissam Medarhri,
  • Mohammed Lamarti Sefian

摘要

In the context of increasingly heterogeneous student populations and a growing emphasis on data-driven decision-making, accurately predicting academic performance remains a m193 ajor challenge. This study investigates the use of regression-based machine learning models to estimate continuous academic outcomes, specifically the final average scores of adolescent students (Patil et al., in Int J Comput Appl 176(22):15–21, 2024, [1]). Data were collected from Moroccan schools using a cluster sampling strategy, following a methodology inspired by prior educational research (Romero et al., in IEEE Transactions on Systems, Man, and Cybernetics, Part C, vol 40, no 6, pp 601–618 (2010), [2]). Several supervised learning algorithms including Linear Regression, Random Forest Regressor, Decision Tree Regressor, and K-Nearest Neighbors Regressor were trained and evaluated using a standard train-test split. Model performance was assessed with standard regression metrics: coefficient of determination ( \(R^2\) ), mean absolute error (MAE), and mean absolute percentage error (MAPE). The ultimate goal is to develop a reliable system that supports the early identification of at-risk students and informs personalized pedagogical interventions. Findings highlight the practical relevance of machine learning in improving academic guidance and individualized learning strategies.