Surface roughness plays an important role in manufacturing and the product quality depends on the surface roughness. The present work focuses on developing a multiple regression model with intercepts for the prediction of surface roughness in milling. The working parameters, viz. speed, feed and depth of cut are considered in this model. The experiments were conducted based on factorial design in Design of Experiments (DOE). The values surface roughness predicted by this model are then verified with additional experiments and compared. Experimental results and statistical tests demonstrate that the model developed in this work predicts the surface roughness values with good accuracy.