Generalized Additive Model

Similar to GLM but we allow any weight function (can be nonlinear too)

g(EY(y∣x))=β0+f1(x1)+f2(x2)+…+fp(xp)g\left(E_Y(y \mid x)\right)=\beta_0+f_1\left(x_1\right)+f_2\left(x_2\right)+\ldots+f_p\left(x_p\right)

So we add a set of basis functions for each feature as new features.