Scholarlink

For educational institutions, forecasting students’ academic performance is a significant problem that helps them foresee academic failure and enhance their teaching methods. A number of models have been put forth to examine and forecast academic results using educational data as machine learning techniques have grown in popularity. Three popular classification algorithms Logistic Regression, Random Forest, and AdaBoost are compared in this article. Standard measures including accuracy, recall, F1 score, and AUC-ROC are used to assess the models on a Student Performance Prediction Dataset. The experimental results demonstrate the efficacy of ensemble approaches for modeling academic achievement, with AdaBoost and Random Forest in particular outperforming Logistic Regression in terms of predictive performance.

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

Intelligent Student Performance Prediction Using Ensemble Classification Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Nadia Saidi,
  • Mohammed Ngadi,
  • Saadeddine Igamane,
  • Aouatif Amine,
  • Hanaa Hachimi

摘要

For educational institutions, forecasting students’ academic performance is a significant problem that helps them foresee academic failure and enhance their teaching methods. A number of models have been put forth to examine and forecast academic results using educational data as machine learning techniques have grown in popularity. Three popular classification algorithms Logistic Regression, Random Forest, and AdaBoost are compared in this article. Standard measures including accuracy, recall, F1 score, and AUC-ROC are used to assess the models on a Student Performance Prediction Dataset. The experimental results demonstrate the efficacy of ensemble approaches for modeling academic achievement, with AdaBoost and Random Forest in particular outperforming Logistic Regression in terms of predictive performance.