Nitrogen has been valued as an economical alternative injection gas for gas-based enhanced oil recovery (EOR) processes. Minimum miscibility pressure (MMP) is the most important parameter to successfully design N-2 flooding. In this communication, a data bank covering wide ranges of thermodynamic and compositional conditions was gathered from open literature. Afterward, a rigorous approach, namely least square support vector machine (LSSVM) optimized with coupled simulated annealing (CSA) was proposed to develop a reliable and robust model for the prediction of MMP of pure/impure N-2-crude oil. The results of this study showed that the proposed model is more reliable and accurate than the preexisting models in a wider range of thermodynamic and process conditions. The proposed model predicts the total dataset (84 MMP data points of pure N-2, nitrogen mixture streams and lean gases) with an average absolute relative error of 5.17%. Finally, by employing the relevancy factor, it was found that the intermediate components of crude oil have the most significant impact on the nitrogen MMP estimation and Leverage approach shows that only two data points (2.4%) are outside the applicability domain of the model proving the reliability of the developed model. (C) 2016 Elsevier Ltd. All rights reserved.