Scholarlink

<p>The educational process is necessary in producing a generation capable of steering the nation toward progress in all spheres of life. This study investigates the classification of student grades using machine learning techniques. Experiments were conducted using a dataset of 504 samples from higher secondary schools of Jammu District, applying two transfer learning models: K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). Among these models, SVM emerged as the best performer. However, the ensemble model (SVM + KNN) appeared to generalize effectively on the dataset, with accuracy rates of 90.10%. Thus, it can be concluded that deeper and more optimized architectures are better suited for the task of students’ grade classification. The study shows that machine learning can automate grade classification, enabling early performance prediction that helps teachers provide timely support to struggling students, boosting success rates, identifying improvement areas, and transforming teaching and learning.</p>

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

Implementing a hybrid machine learning technique that merges SVM with KNN to anticipate students' academic achievements

  • 期刊论文

  • 发表日期：

    2025年11月21日

查看全文
  • Minakshi Sharma,
  • Vibhakar Mansotra

摘要

The educational process is necessary in producing a generation capable of steering the nation toward progress in all spheres of life. This study investigates the classification of student grades using machine learning techniques. Experiments were conducted using a dataset of 504 samples from higher secondary schools of Jammu District, applying two transfer learning models: K-Nearest Neighbors (KNN) and Support Vector Machine (SVM). Among these models, SVM emerged as the best performer. However, the ensemble model (SVM + KNN) appeared to generalize effectively on the dataset, with accuracy rates of 90.10%. Thus, it can be concluded that deeper and more optimized architectures are better suited for the task of students’ grade classification. The study shows that machine learning can automate grade classification, enabling early performance prediction that helps teachers provide timely support to struggling students, boosting success rates, identifying improvement areas, and transforming teaching and learning.