In this paper, we put forward a neural network approach to predict existing and infill oil well performance. Multiple wells' history production data were used to train the neural network and the established neural network can be used to predict future performance of oil wells. No reservoir data is currently involved in the establishment of neural network; therefore, it can predict well production performance in absence of reservoir data. As both of the static and dynamic data are used in the training, we combine the spatial and time series prediction together in this approach. Primary production of a 9-well area in North Robertson Unit located in west Texas was tested in this paper. The results demonstrate that our approach is powerful in rapid projection of existing wells' future performance, as well as the performance prediction of infill drilling wells. By incorporating the appropriate optimization technique, it can be further extended to use for location optimization of infill drilling wells.