QSPR studies for predicting gas to acetone and gas to acetonitrile solvation enthalpies using support vector machine

► Gas to acetone and gas to acetonitrile solvation enthalpies were modeled using QSPR approaches. ► GA-PLS was used to select the optimal subset of molecular descriptors. ► PLS, ANN and SVM were used for prediction of solvation enthalpy. ► The performances of the SVM model were superior to those of PLS and ANN ones.