• S.Suvetha
• C.Immaculate Mary

In educational data mining (EDM) student performance prediction had evolved as an important research domain. The primary aim is to predict the student outcome and to analyse the student at risk which helps the institutions to improve the education quality and makes better decisions. This study proposes a structured analysis which focuses on predicting student marks using different regression-based machine learning models. The dataset, sourced from the UCI Machine Learning Repository it incorporates demographic, socioeconomic, and academic factors as predictive features. Multiple regression algorithms, such as Linear Regression, Ridge Regression, Lasso Regression, Decision Tree Regressor, Random Forest Regressor, Gradient Boosting Regressor, and XGBoost Regressor were implemented and evaluated using cross-validation technique and residual analysis. Each model performance was analyzed through various performance metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). The results indicate that Lasso Regression achieved the highest predictive accuracy (R² = 0.874, RMSE = 1.18) which outperforms other models, while ensemble methods such as Random Forest and Gradient Boosting also delivered competitive results. In contrast, Decision Tree exhibited lower performance because of high error rates.

Educational data mining, Machine learning, Student performance prediction, Regression models, Residual analysis, Model comparison.

"A Regression-Based Machine Learning Approach for Student Performance Prediction with Cross-Validation Stability", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.f7-f15, September-2025, Available :http://www.jetir.org/papers/JETIR2509502.pdf

"A Regression-Based Machine Learning Approach for Student Performance Prediction with Cross-Validation Stability", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppf7-f15, September-2025, Available at : http://www.jetir.org/papers/JETIR2509502.pdf