Abstarct: In this project, a quantitative structure – property relationship (QSPR) study was conducted on the solubility parameters of 70 polymer solvents in the first part and on the retention indices (RI) of 70 essential oil compounds in second part. The solubility parameter (δ) is an intrinsic physicochemical property of a substance. It provides an easy numerical method of fast prediction the basic properties of materials. One of the essential functions of the solubility parameter is for evaluating the possibility of mixing between substances. Plant essential oils and their extracts have been extensively employed in folkmedicine, for flavoring food, and in thefragrance and pharmaceutical industries The stepwise regression method was used as descxriptor selection. Tow linear (Multiple Linear Regression; MLR) and nonlinear (Artificial Neural Network; ANN) methods were used to constructions of odels. The models were validated using external set, as well as leave one out and Y-Randomization techniques. Both linear and nonlinear methods have good prediction ability, although ANN model has more accurate results. In the first section of this study, the correlation coefficient (R) of the test set obtained by MLR and ANN models were 0.968 and 0.975 respectively. In the second part, the correlation coeficient of the test set obtained by MLR and ANN models were 0.949 and 0.964 respectively.