This research proposed an advance in the prediction of the in-process surface roughness during the ball-end milling process by utilizing the wavelet transform to monitor and decompose the dynamic cutting forces. The chatter detection system has been adopted from the previous research of the author to avoid the chatter first, and hence, the dynamic cutting force ratio is introduced to predict the in-process surface roughness during the normal cutting by taking the ratio of the decomposed dynamic cutting force in X axis to that in Z axis. The Daubechies wavelet transform is employed in this research to analyze the in-process surface roughness. The experimentally obtained results showed that the surface roughness frequency occurred at the same level of the decomposed dynamic cutting forces although the cutting conditions are changed. It is understood that the in-process surface roughness can be predicted effectively under various cutting conditions referring to the proposed monitoring system.