SBS exam result prediction model

This research aims to predict the academic performance of middle school students using machine learning algorithms applied to performance, demographic, and survey data. In this study, we evaluated the effectiveness of each algorithm on individual and combined datasets using Multiple Linear Regression (MLR), Support Vector Machine (SVM), and Convolutional Neural Network (CNN) with 5-fold cross- validation. Performance is evaluated with Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), R-squared (r2) criteria. In this study, comparative analysis was used to determine the optimal strategy for educational data analytics by revealing significant differences in model accuracy and computational efficiency. This research aims to contribute to educational data mining and improve educational strategies and interventions by providing a detailed evaluation of machine learning techniques for predicting student performance.