A look at the number of publications in the last decades on the prediction of hydrate forming conditions for various gas mixtures obviously indicates the importance of this field from scientific and industrial viewpoints. Yet, the correlations presented in the literature are not accurate enough and also some of these correlations are presented mainly in graphical form, thus making it difficult to use them within general computer packages for simulation and design. In this study adaptive neuro-fuzzy inference systems were used to produce a nonlinear model to predict the hydrate formation temperature. The model was trained using 303 input-output patterns collected from reliable sources. The adaptive neuro-fuzzy inference system model enables the user to accurately predict hydrate formation conditions under varying system conditions (i.e., temperature, pressure, and gas composition), without having to do costly experimental measurements. Also, statistical error analysis is used to evaluate the performance and the accuracy of the adaptive neuro-fuzzy inference system for estimating natural gas hydrate formation to guide designers and operators in selecting the best system conditions for their particular applications. It is shown that the results of predictions are in acceptable agreement with experimental data indicating the capability of the adaptive neuro-fuzzy inference system for predicting hydrate formation conditions of natural gases.