Search

This comparative study explores machine learning algorithms—Ridge regression, Lasso regression, Decision Tree, and Random Forest—for estimating the compressive strength of High-Performance Concrete. Performance metrics such as Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared (R²) are employed for evaluation. Notably, Random Forest emerges as the standout performer, exhibiting superior accuracy with the lowest RMSE of 10.17 and a minimal MAPE of 8.89. Lasso regression follows closely, showcasing effective error minimization. The study underscores the practical implications of algorithm selection, emphasizing the importance of considering interpretability and accuracy trade-offs. These findings provide valuable insights for practitioners and researchers navigating the application of machine learning to concrete strength estimation. [ABSTRACT FROM AUTHOR]