The interaction between water and solid surfaces is an active area of research, and the interaction can be generally defined as hydrophobic or hydrophilic depending on the level of wetting of the surface. This wetting level can be modified, among other methods, by applying coatings, which often modify the chemistry of the surface. With the increase in available computing power and computational algorithms, methods to develop new materials and coatings have shifted from being heavily experimental to including more theoretical approaches. In this work, we use a range of experimental and computational features to develop a supervised machine learning (ML) model using the XGBoost algorithm that can predict the water contact angle (WCA) on the surface of a range of solid polymers. The mean absolute error (MAE) of the predictions is below 5.0°. Models composed of only computational features were also explored with good results (MAE <
5.0°), suggesting that this approach could be used for the "bottom-up" computational design of new polymers and coatings with specific water contact angles.