Laser Powder Bed Fusion (L-PBF) is one of the most important metal additive manufacturing (AM) methods, with various applications in industries such as the medical and automotive sectors, where precision and customization are essential. This research emphasizes integrating machine learning (ML) techniques with experimental analyses to optimize L-PBF processes. It provides critical insights into the interplay among process parameters, microstructure, and mechanical performance. This study employs ML to model the relationship between process parameters and relative density in AISI 316L stainless steel components containing 2.5% copper, produced via L-PBF. Support Vector Regression (SVR) was identified as the most precise algorithm for predicting relative density, with an accuracy of over 99%, enabling the optimization of process parameters to achieve desired outcomes such as high density, improved surface quality, or enhanced productivity. Subsequently, microstructural and mechanical properties were analyzed to provide deeper insights into material behavior. Microstructural investigations using Scanning Electron Microscopy (SEM) and Optical Microscopy (OM) revealed substantial transformations, including forming equiaxed and columnar cells attributed to copper addition. Irregular grains were observed, resulting from the rapid solidification characteristic of the L-PBF process. Notably, copper fully dissolved into the austenitic phase with no evidence of segregation, leading to increased lattice distortion, reduced crystallite size, and enhanced hardness. Melt pool dimensions were analyzed across samples with varying process parameters, establishing correlations with porosity levels and microstructural refinement. Additionally, in-situ alloying with copper was found to improve mechanical properties slightly. Tensile testing further explored the relationship between porosity and mechanical properties, providing a comprehensive understanding of the impact of process parameters and material composition on overall performance. SEM analysis of the fracture surfaces identified both brittle and ductile failure mechanisms. Brittle fractures exhibited quasi-cleavage planes, likely aligning with melt pool boundaries, while ductile fractures displayed extensive dimple networks.