Accurate predictive modeling is an essential prerequisite for optimization and control of production in modern manufacturing environments. For slender bar turning operations, dimensional deviation is one of the most important product quality characteristics due to the low stiffness of part. In this study, radial basis function neural network is employed to investigate dimensional errors in slender bar turning. The relationship between cutting parameters and dimensional errors is firstly described by the proposed model. Simulation is provided to investigate the effects of cutting parameters on dimensional errors. Further, real-time predictive model based on radial basis function neural network is developed to perform the dimensional error monitoring during slender bar turning process. Experiments verify that the proposed in-process predictive system has the ability to monitor efficiently dimensional errors within the range that they have been trained.