Determining the properties of Crushed Rock Powder, Cement, Sand and Coarse Aggregate (CRPCSC) particulate composite in a conventional way by conducting the experiments is time consuming and requires men and material. In the present study an effort is made to predict the spilt tensile strength and slump values of M20 and M35 grade CRPCSC particulate composite using artificial neural network (ANN). ANN is a computational model that is inspired by structure and functional aspects of biological neural network. ANN is used in many areas of research and development. In this study experimental results reported by earlier researchers are used. In the present study the spilt tensile strength and slump values of M20 and M35 grade CRPCSC particulate composite with different percentages of crushed rock powder replacement for sand is predicted. The results are also compared with conventional particulate composite (CSC) to find the optimum percentage of CRP replacement to sand. In the analysis, mix design proportion of CRPCSC particulate composite is used as input data to obtain the predicted values of split tensile strength and slump as output from ANN. Analysis of input and output data, network training, network testing and their validation is conducted and the results obtained from ANN analysis were comparable with the experimental results of CRPCSC report. © The Society for Experimental Mechanics, Inc. 2014.