Comparative modeling for academic performance prediction
This project implements and compares regression models — including Linear Regression and Random Forest — to predict academic scores using structured numerical features. It supports educational planning through interpretable modeling and performance metrics.
Best Model: Linear Regression
R² Score: 0.88 | RMSE: 2.73
Linear Regression achieved the highest stability and accuracy across validation folds, outperforming Random Forest on interpretability and generalization.
Histograms for each input variable
Visual overview of feature correlations
Prediction comparison for both models
MAE, RMSE, and R² scores
Lollipop chart for Random Forest importance
Bar chart of Linear Regression coefficients