The estimation of concrete compressive strength is utmost important for the construction of a building. Organizations have a limited budget for mix design; therefore, proper estimation of concrete data has a significant impact on site operations and the construction of the building. In this paper, the prediction of concrete compressive strength is done by Multivariate Adaptive Regression Spline (MARS), Least Squares Support Vector Machine (LSSVM) and genetic programming (GP) which is a very new approach in the field of concrete technology. MARS is a supervised technique, performs well for high dimensional data, interacts less with the input variables, whereas LSSVM is generally based on a statistical learning algorithm and GP builds equations that are generated for modeling. All the developed LSSVM, MARS and GP gives an equations for prediction of compressive strength which makes easy to predict the compressive strength of the concrete. The efficiency of the MARS, LSSVM and GP are measured by the comparative study of the statistical parameters and can be concluded that the all the models performed very well as the output results are very close to the desired value, while the MARS slightly outperformed the other two models. © 2020, Chulalongkorn University, Faculty of Fine and Applied Arts. All rights reserved.