Kidney transplantation is the treatment of choice for patients with end-stage renal disease, significantly improving survival and quality of life. However, graft failure remains a leading cause of morbidity and return to dialysis, for which current clinical risk assessment tools show limited accuracy. The availability of large transplant registries has enabled the application of Machine Learning (ML) approaches to enhance post-transplant risk prediction. In this study, data from the Scientific Registry of Transplant Recipients (SRTR/UNOS) were analyzed, including 172,881 adult kidney transplant recipients in the United States between 2018 and 2025. Only pre-transplant donor and recipient variables available at the time of transplantation were used as model inputs.