Wettability is a crucial surface feature of polymers due to their numerous interaction-destined applications. This study focuses on the application of sand blasting process for investigating the wettability of polymeric materials to produce hydrophobic behavior. Four different polymeric materials, Acrylonitrile Butadiene Styrene (ABS), Poly(methyl methacrylate) (PMMA), Polypropylene (PP), and Polycarbonate (PC) underwent sand blasting with varying process parameters, following a comprehensive plan for the design of experiments. Subsequent analyses included surface roughness measurement and wettability tests, supplemented by scanning electron and confocal microscopy observations to gain deeper insights into the blasted surfaces. A predictive model based on a machine learning algorithm was developed using the backpropagation technique to correlate the surface treatment parameters to surface roughness and wettability indexes. From the experimental results sand blasting proved to be efficient in creating hydrophobic surfaces on all the tested materials. The developed neural network demonstrated high fitting degrees between the predicted and measured values. ABS exhibited the most hydrophobic behavior and emerged as a strong candidate for further investigations.