This study focuses on predicting surface roughness parameter Ra for 3D-printed parts using mathematical modeling and Design of Experiments (DoE). The precision of 3D-printed components is influenced not only by dimensional and geometrical accuracy but also by surface quality, which has a very important role in determining the functionality of the parts. This study investigates the impact of key process parameters, such as the enhanced visible rasters and the enhanced internal rasters on surface roughness parameter Ra. Building on our previous published research that identified an optimal raster angle of 45° and an enhanced internal raster value of 0.5048 mm for improved dimensional accuracy, this study extends the analysis to assess how these and additional parameters affect the surface roughness. By systematically varying these factors, the study aims to identify configurations that minimize the values obtained for the surface roughness Ra. A mathematical model, represented as a cubic equation, was developed using Response Surface Methodology. This model uses process parameters as inputs and Ra as the response variable. Regression analysis was employed to determine the coefficients of the cubic equation, and ANOVA was used to assess the significance of each process parameter. The model’s accuracy was evaluated using statistical metrics such as R2. These results offer manufacturers valuable guidance on optimizing print settings for superior surface finishes. Future research will delve into the interplay of thermal effects, material behavior, and deposition consistency to further improve print quality.