Abstarct: An artificial neural network (ANN) model in quantitative structure property relationship (QSPR) was developed for density prediction of 10 alcohols over a wide range of pressure molecular (0.1-300 MPa) and tempreratures (273.15-338.15K). A large number of descxriptors were calculated by Dragon software and a subset of calculated descxriptors was selected from 18 class of Dragon descxriptors with a stepwise multiple linear regression (MLR) as a feature selection technique. The selected descxriptor that appear in multiple linear regression models is: HGM (Geometric mean on the leverage magnitude). Two calculated and two experimental descxriptors contain: pressure and temperature, were selected as the most feasible descxriptors in the construction of artificial neural network (ANN) models. The data set was randomaly divided into three subset: training (396 point), validation (86) and test set (86). After training and optimization of the ANN parameters, the performance of the model was investigated by the test set. The mean squares error (MSE) were 0.3835 and 0.036 respectively, for the test data set in MLR and ANN methods. The results obtained using ANN were compared with the experimental values as well as with those obtainted using regression models and showed the superiority of ANN over linear multiple regression model.