This study explores the prediction of compressive strength of high-strength concrete (HSC) using advanced artificial intelligence (AI) and machine learning (ML) techniques. As the demand for high-performance concrete continues to rise in modern construction, accurately predicting its compressive strength is crucial for ensuring structural safety and optimizing material usage. Traditional methods of strength prediction often rely on empirical formulas and standard test methods, which may not capture the complexities involved in concrete behavior. In this research, a comprehensive dataset comprising various concrete mixtures was compiled, including parameters such as water-cement ratio, aggregate type, admixture content, and curing conditions. Multiple machine learning algorithms, including linear regression, support vector machines (SVM), random forest, and artificial neural networks (ANN), were employed to analyze the dataset and develop predictive models for compressive strength. The performance of each model was evaluated using statistical metrics such as mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²). The results indicate that the machine learning models, particularly the ANN, demonstrated superior accuracy in predicting compressive strength compared to traditional approaches. The developed predictive models offer a reliable tool for engineers and researchers to optimize concrete mixtures, leading to improved material efficiency and cost-effectiveness. This study highlights the potential of AI and ML techniques in the field of civil engineering, particularly in concrete design and quality control. By integrating these advanced technologies into the concrete production process, it is possible to achieve more sustainable construction practices and enhance the performance of high-strength concrete in various applications. Future research will focus on refining these models further and exploring their applicability to other concrete properties and performance indicators..

strength concrete; prediction; genetic engineering programming