Understanding the relationship between structural and functional connectivity remains a crucial issue in modern neuroscience. Here we investigate such relationship through a stochastic neural whole-brain model, using as input the structural connectivity matrix defined by the human connectome. Importantly, we address the structure-function relationship both at the group and individual-based levels. In this work, we show that equalization of the nodes excitatory input improves the correlation between simulated neural patterns of the model and various brain functional data. We find that the best model performance is achieved when the model control parameter is in its critical value and that equalization minimizes both the variability of the critical points and neuronal activity patterns among subjects. Our results open new perspectives in personalized brain modelling with potential applications to investigate the deviation from criticality due to structural lesions (e.g. stroke) or brain disorders.