The advent of 3D printing technology has revolutionized manufacturing processes, offering accelerated prototyping, intricate geometry creation, and sustainable practices. Achieving high-quality prints necessitates precise estimation of surface roughness and extruder temperature. Fluctuations in extruder temperature leads to low tensile strengths and nozzle clogging. Friction and wear result in poor surface roughness. This research employs machine learning (ML) techniques to predict surface roughness and extruder temperature based on various printing parameters, aiming to enhance the overall quality of 3D-printed objects. Key objectives include identifying process parameters affecting surface roughness and extruder temperature, training and testing various ML algorithms, and evaluating models using criteria such as mean absolute error, root mean squared error, and R-squared value. Eight ML algorithms are considered, with random forest and XGBoost demonstrating superior performance for extruder temperature and surface roughness, respectively. The utilization of ML algorithms enables accurate prediction of surface roughness and extruder temperature, contributing to improved quality performance in additive manufacturing processes.