The results of NN models, if constructed properly, generally yield a more realistic and accurate predictions. NN models are constructed based on simulating the structure and learning activities of the human brain. Garrett et al. (1997) defines a NN model as "a computational mechanism able to acquire, represent, and compute mapping from one multivariate space of information to another, given a set of data representing that mapping". This study is intended to estimate the stiffness modification factor for the coupling beam of coupled shear walls using a neural network model. In mid and high rise R/C buildings, shear wall and coupled shear wall (CSW) systems are usually