Shear walls are the type of structural systems that provide the lateral resistance to a building or structure. Lateral loads are applied on one plate and along the vertical dimension of the wall. These type of loads are usually transmitted to the wall collectors. Concrete shear walls have a considerable resistance to lateral seismic loading. Model prediction is required for the shear capacity of these walls to ensure the seismic security of the building. Therefore, a model is proposed to estimate the shear strength of concrete walls using an artificial intelligence algorithm. The input parameters of the neural network include the thickness of the reinforced concrete shear wall, the wall length, the vertical reinforcement ratio, the transverse reinforcement ratio, the compressive strength of the concrete, the stresses of the transverse reinforcement, the stresses of the vertical reinforcement, the ratio of the dimensions. The target parameter is the shear strength of the reinforced concrete shear wall. A total of 58 laboratory data was collected on concrete shear walls. The results of the research show that optimum artificial neural network with a specific number of hidden neurons can accurately estimate the shear capacity of reinforced concrete shear walls. The results indicate that the highest percentage of effect and the lowest percentage of effect have a target function. Additionally, the error rate obtained for predicting shear capacity is 7%, which is an acceptable error in this regard.