Concrete is a simple, versatile, and powerful material which is frequently used in construction practices due to its strength, and adaptability. Machine learning (ML), a subfield of artificial intelligence, has the ability to identify patterns in data and draw conclusions. With the prediction of the compressive strength (CS) of concrete, ML fosters innovation across many industries including the construction sector as it saves resources and efforts in laboratory testing. ML algorithms use a range of parameters, such as component proportions, curing days, and types of aggregate, to predict the CS of concrete. By examining enormous datasets for patterns and correlations, these algorithms revolutionize the building process. CS is the important output parameter which is taken per many studies in which various waste materials are used such as Fly ash, Ground Granulated Blast Furnace Slag (GGBS) and others. Furthermore, various ML models Decision Tree (DT), Artificial Neural Network (ANN), and many more have been used to examine the CS of concrete. Based on the comprehensive literature review, the aim of the current article is to provide the essential information about varies aspects involved during the prediction of CS of concrete mixes with and without supplementary cementitious material. In addition, special emphasis has been given on the factors that should be considered while choosing different types of dataset, models, visualization plots and performance measuring matrices. A dedicated section with the focus on the recommendations for the future studies has also been added for the better understanding the concept of compressive strength prediction.