Two extrusion experiments using a single screw extruder were conducted with an ingredient blend containing 40% DDGS, along with soy flour, corn flour, fish meal, vitamin mix, and mineral mix, with the net protein content adjusted to 28%. The variables controlled in the first experiment included 7 levels of die size, 3 levels of moisture content, 3 levels of temperature gradient in the barrel, and one screw speed. The variables altered in the second experiment included 3 levels of moisture content, 3 levels of temperature gradient in the barrel, 5 levels of screw speed, and one die size. Regression models and Neural Network (NN) models were then developed using the data pooled from the two experiments to predict extrudate properties and extrusion processing parameters. In general, both regression and NN models predicted the extrusion processing parameters with better accuracy than the extrudate properties. With the regression modeling, even though increasing the number of input variables from 3 to 6 resulted in better R2 values, there was no significant decrease in the coefficient of variation between the measured and predicted variables. On the other hand, the NN models developed with 3 input variables (L/D ratio of die, moisture content and temperature gradient) predicted the extrusion processing parameters and extrudate properties with better accuracy than the regression models developed with the same 3 input variables. Furthermore, increasing the number of input variables resulted in better accuracy of prediction for both extrudate properties and extrusion processing parameters, and the standard error and coefficient of variation were also found to decrease. The highest accuracy of prediction was observed for the NN models developed to predict the extrusion processing parameters with 6 input variables (D, L, L/D ratio of die, moisture content, temperature gradient and screw speed). Because of its ability to account for variation, NN modeling has great potential for developing robust models for extrusion processing.