The present research was purposed to estimate the heat of vaporization for petroleum fractions and pure hydrocarbons by the lease square support vector machine (LSSVM) as a function of the specific gravity, molecular weight, and boiling point temperature. Moreover, a particle swarm optimization (PSO) technique was applied to determine the optimal dependent parameters of LSSVM. Results obtained from the proposed LSSVM model have been compared to some developed correlations by scholars. According to statistical observations, the LSSVM model has acceptable predictions by the value of mean relative deviation (MRD) and R-squared (R-2) equal to 0.51% and 0.9998, respectively. Moreover, accurate predictions by developed LSSVM model was proved against previously developed correlations. The present predictive manner can be used in petroleum engineering for an accurate approximation of heat of vaporization.