Abstract : This paper explores the application of machine learning algorithms in predicting the compressive strength of high-performance concrete (HPC), a critical aspect of ensuring structural integrity in modern construction. Various machine learning models—such as XGBoost, K-nearest neighbors (KNN), Decision Tree, and Random Forest—were evaluated to predict HPC strength with high accuracy. The study compares the performance of these models using metrics like R², MAE, and RMSE to identify the most effective approach. Results indicate that XGBoost outperformed other models like decision Tree KNN and Random Forest. Feature importance analysis highlighted key factors influencing HPC strength, such as age, cement, and water-to-cement ratio. These findings emphasize the potential of machine learning in improving quality control for HPC and optimizing mix design processes. Future work will explore the integration of environmental factors and advanced hybrid models to further enhance prediction accuracy.