Concrete, the most often utilized construction material, is a composite of cement, fine aggregates, coarse aggregates, water and admixtures. The significant property of hardened concrete is its characteristic compressive strength. It is conventionally tested by casting concrete cubes of standard dimensions and testing them using the compression testing machine. In the present study, an attempt is made to develop machine learning models to predict the compressive strength of concrete using several machine learning algorithms. The dataset sourced from GitHub platform consists of 1030 observations. The selected feature variables are quantities of ingredients in one cubic meter of concrete and the age of concrete and the target variable is the compressive strength of the concrete in MPa. The performance of each model is evaluated using indices, like MAE, RMSE and R2 and it is observed that among the developed models Random Forest has the best performance with R2 = 0.90. Once a sufficiently accurate model is established, it can substitute or complement conventional testing methods, saving time and costs in construction processes while enhancing efficiency. This approach highlights the practical implications of ML in the construction industry.