Calcined clay cements have the potential to reduce the carbon footprint of the cement production sector. However, accurately predicting the engineering properties of this low carbon cement remains challenging due to the numerous parameters involved in formulation and hardening processes. Machine learning (ML) algorithms have shown promising prediction performance for Portland cement, and their effectiveness for calcined clay cement is expected due to their data-driven nature. In this study, the ML approach was leveraged to predict the influence of material composition and hardening conditions on the compressive strength of calcined clay cement. Seven supervised ML algorithms are employed, considering fourteen input features including clay, Portland cement, and limestone percentages, chemical composition expressed as reactivity ratios, clay calcination conditions, and hardening conditions. The targeted feature is the compressive strength. Through evaluation, the XGboost algorithm emerges as the most accurate predictor, yielding a mean absolute error of 2.5 MPa. The findings reveal that the alumina-to-silica ratio of clay significantly impacts the development of cement strength. Furthermore, the ML model predicts a decrease in strength above 920°C, consistent with experimental results reported in the literature. The developed ML model not only confirms previous experimental findings but also identifies promising potential formulations based on calcined clay for further experimentation. It is important to note that the carbon footprint of the compositions predicted by the ML model requires a comprehensive life cycle assessment, which goes beyond the specific research question of this paper.