Oil viscosity is one of the main parameters that plays a governing role in reservoir fluid calculations, fluid flow through porous media, enhanced oil recovery methods, pipeline designs, etc., so it is of great importance to use an accurate method to calculate the oil viscosity at various operating conditions. In the literature, several empirical correlations have been proposed for predicting oil viscosity. However, these correlations are not able to predict the oil viscosity adequately for a wide range of conditions. In the present work, extensive experimental data of dead, saturated, and undersaturated oil viscosities from different samples of Iranian oil reservoirs were applied to develop an artificial neural network (ANN) model to predict and calculate the oil viscosity. By comparing the obtained results using the developed ANN model and other correlations with experimental data, it was observed that there is more qualitative and quantitative agreement between ANN model results and experimental data. Furthermore, the developed ANN model shows more accurate prediction over a wide range of operating conditions.