Defining the relationship between the quality of Injection molded parts and the process condition is very complicate because of lots of factors are involved and each factor has a non-linearity. With the development of CAE(Computer Aided Engineering) technology, the estimation of volumetric shrinkage of injection mold parts is possible by computer simulation in spite of restricted application. In this research, the Taguchi method md Neural Network are applied for finding optimal processing condition. The percent of volumetric shrinkage is compared on each case and shows neural network can be successfully applied.