• Srajan Kumar Choubey

This study explores the application of various machine learning algorithms in predicting the compressive strength of concrete. The models used for analysis include Decision Tree, Random Forest, Bagging, Gradient Boosting, and Neural Networks. A comparative evaluation is conducted based on key performance metrics such as R², Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results demonstrate that Gradient Boosting outperforms other models, achieving an R² of 0.898 and the lowest MSE. The study further discusses the feature importance of concrete mix constituents and proposes potential improvements for predictive modeling for compressive strength of concrete.

Gradient Boosting, Compressive Strength, Concrete Strength Prediction, Machine Learning in Concrete, Predictive Modeling

"Predicting Compressive Strength of Concrete using Machine Learning Algorithm: A Comparative Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.h758-h764, December-2024, Available :http://www.jetir.org/papers/JETIR2412790.pdf

"Predicting Compressive Strength of Concrete using Machine Learning Algorithm: A Comparative Analysis ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. pph758-h764, December-2024, Available at : http://www.jetir.org/papers/JETIR2412790.pdf