One of the major aerodynamic noise generation mechanisms is the interaction of a turbulent flow with a downstream blunt object, such as the blade of a rotating fan or a fixed stator. A possible method to reduce this noise is the use of flow-permeable leading edges, which has been investigated experimentally on a set of flat plates with different leading-edge perforations. The results show that these modifications can lead to notable noise reductions at low and medium frequencies, but also to a noise increase at high frequencies due to the contribution of surface roughness noise. The measured data were then used as an input to a symbolic regression modeling approach with the aim of obtaining a simple yet accurate model to predict the noise reduction capacity of the permeable leading edges. Three different prediction models were finally selected to demonstrate the capability of the current approach. One of the more complex models already predicts correct trends and shows an acceptable mean absolute error, making it a reliable candidate for engineering purposes.