This study explores the application of machine learning techniques for real-time monitoring and optimization of the 3D printing process. When it tries to enhance the quality and accuracy of printed objects by merging them with machine-learning models. To address this, we developed predictive models capable of adjusting printing settings in real-time to optimize printing quality and mechanical properties that can be also enhanced with enrichment datasets. This study was implemented on a Kaggle dataset of the Ultimaker S5 3D printer. Moreover, we applied several machines learning algorithms, including Random Forest, Support Vector Machines (SVM), and Deep learning to predict the impact of various printing parameters on the final product quality. In addition, this study demonstrates the variation in printer settings such as layer height, infill density, and nozzle temperature, and how it affects the tensile strength, roughness, and elongation of printed objects. Our suggestion that real time data-driven adjustments can surely enhance output quality while reducing material wastage showcasing the potential of integrating advanced machine learning models into additive manufacturing processes. This research contributes to the field by demonstrating the feasibility and benefits of using machine learning for dynamic optimization in 3D-printing. Finally, we found that the SVM model is the best for our implementation with an accuracy of 0.89.