JCE_V5_N2_RP3 Prediction of Compressive Strength of Concrete by Data-Driven Models Faezehossadat Khademi Mahmoud Akbari Sayed Mohammadmehdi Jamal Journal on Civil Engineering 2249 - 0779 5 2 16 23 Concrete, Compressive Strength, Multiple Linear Regression model (MLR), Artificial Neural Network (ANN) The aim of this study is prediction of 28-day compressive strength of concrete by data-driven models. Hence, by considering concrete constituents as input variables, two data-driven models namely Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) models are constructed for the purpose of predicting the 28-days compressive strength of different concrete mix designs. Comparing the two models illustrates that MLR model is not a suitable model for predicting the compressive strength; however, ANN can be used to efficiently predict the compressive strength of concrete. March - May 2015 Copyright © 2015 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=3350