This study explores the use of machine learning (ML) models to predict concrete compressive strength (CS), a critical parameter in structural design. The research analyzes 1030 experimental CS data from previous studies, using both non-ensemble and ensemble ML models. Non-ensemble models include regression-based, evolutionary, neural network, and fuzzy-inference-system approaches, while ensemble models consist of adaptive boosting, random forest, gradient boosting, and categorical gradient boosting. The input parameters are cement, blast-furnace slag, aggregates, fly ash, water, superplasticizer, and curing days, with CS as the output. Comprehensive performance evaluations, including visual and quantitative methods, k-fold cross-validation, and sensitivity analysis using Shapley-Additive-exPlanations (SHAP), were conducted to assess the models' reliability and accuracy. The results indicate that the Categorical-Gradient-Boosting (CatBoost) model achieved the highest accuracy, with a determination coefficient (R²) of 0.966 and a Root-Mean-Square-Error (RMSE) of 3.06 MPa. The SHAP analysis revealed that age was the most influential factor in predicting CS. Additionally, a Graphical User Interface (GUI) was developed to facilitate quick and cost-effective prediction of CS for designers. The study highlights the effectiveness of ML models in enhancing the prediction accuracy of concrete CS, making them a valuable tool for structural engineers.This study explores the use of machine learning (ML) models to predict concrete compressive strength (CS), a critical parameter in structural design. The research analyzes 1030 experimental CS data from previous studies, using both non-ensemble and ensemble ML models. Non-ensemble models include regression-based, evolutionary, neural network, and fuzzy-inference-system approaches, while ensemble models consist of adaptive boosting, random forest, gradient boosting, and categorical gradient boosting. The input parameters are cement, blast-furnace slag, aggregates, fly ash, water, superplasticizer, and curing days, with CS as the output. Comprehensive performance evaluations, including visual and quantitative methods, k-fold cross-validation, and sensitivity analysis using Shapley-Additive-exPlanations (SHAP), were conducted to assess the models' reliability and accuracy. The results indicate that the Categorical-Gradient-Boosting (CatBoost) model achieved the highest accuracy, with a determination coefficient (R²) of 0.966 and a Root-Mean-Square-Error (RMSE) of 3.06 MPa. The SHAP analysis revealed that age was the most influential factor in predicting CS. Additionally, a Graphical User Interface (GUI) was developed to facilitate quick and cost-effective prediction of CS for designers. The study highlights the effectiveness of ML models in enhancing the prediction accuracy of concrete CS, making them a valuable tool for structural engineers.