This paper adopts Minimax Probability Machine Regression (MPMR), Multivariate Adaptive Regression Spline (MARS), and Least Square Support Vector Machine (LSSVM) for prediction of surface and hole quality in drilling of AISI D2 cold work tool steel with uncoated titanium nitride (TiN) and titanium aluminum nitride (TiAlN) monolayer-and TiAlN/TiN multilayer-coated-cemented carbide drills. MPMR is a probabilistic model. MARS is a nonparametric regression technique. LSSVM is developed based on statistical learning algorithm. Cutting tool (t), Feed rate (fr)(mm/rev), and Cutting speed (v)(m/min) have been adopted as inputs of MPMR, MARS, and LSSVM. The output of MPMR, MARS, and LSSVM is Surface roughness (rs) (µm) and Roundness error (re) (µm). A comparative study has been presented between the developed models. The results show that the developed model gives excellent performance.