<p>This paper presents a comparative analysis of various machine learning models for predicting the strength of concrete made with composite cement. Composite cement is a mixture of Portland cement clinker and supplementary cementitious materials, and its strength is a critical factor in the design and performance of concrete structures. The research focuses on evaluating different machine learning (ML) models, such as Regression like Data tree (DT), Support Vector Machine-Regression (SVR), and Artificial Neural Network (ANN) models with suitable neural network tools and neural fitting tools. A comprehensive dataset, consisting of various input variables such as cement components, mix constituents, water-cement ratio, curing and age at testing, is collected from multiple sources to ensure the models' reliability and validity. The performance of the models is evaluated using standard statistical metrics, like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The findings indicate that all three models can predict the strength of composite cement concrete with fair accuracy. The decision tree regression model using coarse tree does not perform well. Medium tree regression exhibits moderate performance, while fine tree results are practically comparable with other ML model results. The SVR model shows promising results for handling complex datasets with numerous features. The ANN model demonstrates strong predictive power, showcasing its ability to capture intricate patterns within the data. The prediction results show that the DT, SVR, and ANN models estimate the compressive strength of composite cement concrete with R² values of 90%, 97%, and 97%, respectively. Moreover, the Root Mean Squared Error (RMSE) for the best-fitting models of the corresponding DT, SVR, and ANN are 3.94, 2.11, and 2.08. These findings suggest that the ANN model effectively captures the intricate patterns in the data, making it the best-performing model. The SVR model also does exceptionally well, coming in a very close second. The study provides valuable insights for construction professionals to optimize concrete mix designs and ensure the structural integrity of built environments. Future research could incorporate additional influential parameters and ensemble learning techniques to further enhance the predictive accuracy of machine learning models for composite cement concrete strength where other supplementary cementitious materials (SCM) with or without fly ash are added to the clinkers.</p>