Scholarlink

In educational data mining, predicting student outcomes is a critical task that can help educators identify at-risk students and tailor interventions to improve educational outcomes. This study explores the effectiveness of various machine learning techniques, including Kernel principal component analysis Kernel PCA, Catboost, Adaptive Lasso and Spearman correlation, in predicting student outcomes. We aim to identify the most important factors influencing student performance and evaluate the predictive accuracy of these methods using DNN, SVM, and KNN on education data composed of these factors from each method.

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

Determinant Factors for Predicting Student Academic Success in Portuguese High Schools

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Abderrafik Laakel Hemdanou,
  • Hamid Barkouk,
  • Mohammed Lamarti Sefian,
  • Youssef Achtoun,
  • Ismail Tahiri

摘要

In educational data mining, predicting student outcomes is a critical task that can help educators identify at-risk students and tailor interventions to improve educational outcomes. This study explores the effectiveness of various machine learning techniques, including Kernel principal component analysis Kernel PCA, Catboost, Adaptive Lasso and Spearman correlation, in predicting student outcomes. We aim to identify the most important factors influencing student performance and evaluate the predictive accuracy of these methods using DNN, SVM, and KNN on education data composed of these factors from each method.