2.1 IntroductionTraditionally, a concrete mix is ​​designed based on code requirements and recommendations which uses empirical values ​​obtained from previous experience. The compressive strength of concrete is determined by performing a standard uniaxial compression test on standard cylindrical specimens aged 7 and 28 days, following the standard procedure and the test values ​​are reported in accordance with ASTM and ACI standards. If the strength value obtained during the test is less than the required strength 28 days after the concrete placing date, the entire process of designing the concrete mix shall be repeated until the value required strength is achieved, which is time-consuming and expensive. Many test samples with different proportions of mix ingredients must be created to achieve the required strength and this is an iterative process. So, every mix designer wants to have a tool or methodology to predict the required compressive strength of concrete at the time of design, before placing the concrete in place. As we know, the relationship between compressive strength and mix ingredients is complex and highly non-linear. Data scientists, researchers and engineers are trying to develop several approaches using the regression function to accurately predict the compressive strength of concrete. Recently, data mining tools have become more popular and reliable methods than others for predicting the compressive strength of concrete. The section below reviews and discusses some of the popular, relevant and effective data mining tools developed so far, for predicting 28-day compressive strength. of concrete.2.2 Multiple regression modelThe first popular regression equation used in the prediction of compressive strength... middle of paper ...... by plasticizer, fine aggregate and coarse aggregate. The least squares method is used to estimate the regression coefficients in the above model. Many researchers have used multiple regression models to improve the accuracy of concrete strength prediction. It is still a popular model because the model once adjusted can predict the required value faster than other modeling techniques and can be easily implemented in computer applications. By performing correlation analysis, it also provides in-depth knowledge on the key factors influencing the 28-day compressive strength of concrete. Although it gives better performance where there are few independent variables, it performs poor modeling when the number of independent variables is higher and the relationship between the independent variables and the dependent variable becomes complex and highly nonlinear..