The well flowing bottom-hole pressure and fluid rates must be known for different applications in the oil and gas industry. The accurate values of these parameters are necessary for different calculations such as gas lift optimization, well monitoring, reservoir performance evaluation, and field development plans. Estimating the values of these parameters without any well intervention is in great demand to minimize the numbers of intervention jobs, operation risk, time, and money. Many correlations are available in the literature to predict these parameters; however, these correlations required knowledge of different variables that are not usually available in accurate values. Searching for a more robust tool for predicting accurate values for these parameters is in demand. Therefore, an artificial neural network (ANN) model was developed from an extracted data set from PROSPER1 software, production logging tool (PLT), and test separator data. First the ANN model was trained and tested by synthetic data (extracted from PROSPER1 software). Then, the ANN model was tested by a group of test points collected from the PLT reports. The developed ANN model yielded an accurate prediction of the well flowing bottom-hole pressure and well fluid rate. The values of these parameters of each well are used to build an integrated production model (IPM) using GAP(2) software to perform different gas lift optimization scenarios.