This Project explores the prediction of surface roughness in Polylactic acid (PLA+) polymer material using Machine Learning (ML) and Additive Manufacturing (3D Printing). Key printing parameters like layer height, infill density, printing speed, nozzle temperature, and printing platform temperature are considered for improving surface morphology. Utilizing machine learning algorithms such as linear regression, support vector machine (SVM), XG-Boost, and random forest regressor, this Project employs Mini Tab Taguchi's Design of Experiment Method to compare model-fit accuracy. The focus is on five influential parameters—layer height, infill density, printing speed, and nozzle temperature using L25 orthogonal array sample datasets to enhance understanding and characterization of the material.