One of the most widely applied models in survival analysis is the Cox proportional hazards model (CPHM). However, modern applications with highdimensional data have put pressure on the model. Together with challengesinherent to survival data, such as censored observations and complex correlation structures, methods have been proposed to improve its predictive accuracy.For this study, we focused on ridge and least absolute shrinkage and selectionoperator (LASSO) penalized CPHM to evaluate how predictive ability changesunder varying settings. By simulating survival data factors including samplesize, number of predictors, correlation, and censoring were controlled and evaluated with concordance index (C-index) and the integrated Brier score (IBS).The results showed small but consistent differences in predictive performancebased on regularization method and evaluation measurement.