Soil nailing has become an important excavation support system for its good performance and cost-effectiveness. It is complicated to predict deformation of soil nailing during excavating. The Artificial Neural Network (ANN) is developed very quickly these years, which can be applied in diverse applications such as complex non-linear function mapping, pattern recognition, image processing and so on, and has been widely used in many fields, including geotechnical engineering. In this paper, the artificial neural network is applied for deformation prediction for soil nailing in deep excavation. The time series neural networks-based model for predicting deformation is presented and used in an engineering project. The results predicted by the model and those observed in the field are compared. It is shown that the artificial neural network-based method is effective in predicting the displacement of soil nailing during excavation.