We focus on short-term wind power forecast using machine learning techniques. We show on real data provided by the wind energy company Maia Eolis, that parametric models, even following closely the physical equation relating wind production to wind speed are out-performed by intelligent learning algorithms. In particular, the CART-Bagging algorithm gives very stable and promising results. Besides, we show on this application that the default methodology to select a subset of predictors provided in the standard random forest package can be refined, especially when there exists among the predictors one variable which has a major impact.