Scholarlink

This paper aims to predict students’ grades using artificial intelligence techniques. Generally, student grades serve as key performance indicators that help tutors monitor their academic progress. We employed various machine learning regressors, including linear regression, Ridge Regression, Least Angle Regression, Bayesian Ridge Regression, Huber Regressor, and other advanced models such as XGBoost, Random Forest, Gradient Boosting, and AdaBoost, for student grade prediction. These techniques can help to improve the student's performance. Linear Regression, Ridge Regression, Least Angle Regression, Bayesian Ridge, and Huber Regressor have the lowest MAE (0.0025), MSE (0%), RMSE (0.0029), RMSLE (0.0008), and R2 (1). These Regression Machine Learning models improve the performance of students’ grade prediction.

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

Evaluating Regression Models for Student Grade Prediction with a Focus on Interpretability and Accuracy

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mounika Tompala,
  • Neelamadhab Padhy,
  • Rasmita Panigrahi,
  • Sibo Prasad Patro

摘要

This paper aims to predict students’ grades using artificial intelligence techniques. Generally, student grades serve as key performance indicators that help tutors monitor their academic progress. We employed various machine learning regressors, including linear regression, Ridge Regression, Least Angle Regression, Bayesian Ridge Regression, Huber Regressor, and other advanced models such as XGBoost, Random Forest, Gradient Boosting, and AdaBoost, for student grade prediction. These techniques can help to improve the student's performance. Linear Regression, Ridge Regression, Least Angle Regression, Bayesian Ridge, and Huber Regressor have the lowest MAE (0.0025), MSE (0%), RMSE (0.0029), RMSLE (0.0008), and R2 (1). These Regression Machine Learning models improve the performance of students’ grade prediction.