<p>This study investigates the influence of supplementary cementitious materials (SCMs) on the compressive strength of cement-sand mortar, aiming to develop a data-driven approach for optimizing SCM use in concrete mixes. The primary objective was to examine the chemical composition of various SCMs, such as fly ash, slag, and silica fume, and their impact on the compressive strength of cement mortar. A comprehensive dataset was compiled from existing literature, including information on SCM types, chemical compositions, and corresponding compressive strength results. Machine learning models, including artificial neural networks (ANN), K-nearest neighbors (KNN), support vector regression (SVR), and extreme gradient boosting (XGBoost), were employed to predict compressive strength based on the chemical composition of SCMs. The results revealed that silica-rich SCMs, particularly silica fume, significantly enhanced compressive strength, while calcium oxide content influenced early strength development. The XGBoost model outperformed other models, offering the best predictive accuracy. The study concludes that the optimal use of SCMs, when carefully proportioned, can enhance compressive strength, with silica and alumina playing key roles. Machine learning models provide an effective tool for predicting strength and optimizing SCM selection. Future research should focus on the long-term durability of SCM-based mortar, explore the synergistic effects of multiple SCMs, and incorporate real-world conditions for further model refinement.</p>