A methodology to predict mechanical properties in injection molded parts has been developed. Knowledge of part properties before actual molding and testing will be of immense help to part and mold designers in modification of design. This methodology involved the application of connectionist learning systems, injection molding computer simulation, and experimental evaluation of mechanical properties, to relate the thermomechanical history of injection molded parts to the resulting part properties so that they can be predicted before parts are molded. The engineering properties of injection molded parts are dependent upon their thermomechanical history which in turn is greatly influenced by the processing conditions and part geometry. As the relationships between engineering properties and thermomechanical history are complex and highly nonlinear, the methodology developed was based on a backpropagation neural network algorithm that provided the means for a nonparametric mapping between the part properties and thermomechanical history. The proposed methodology has been successfully applied to two geometries, plaque and box. This methodology provides designers with the ability to predict mechanical properties in injection molded parts when significant thermomechanical history can be obtained from injection molding simulation.