Lassance, NathanRigal, ArthurArthurRigal2025-05-142025-05-142025-05-142023https://hdl.handle.net/2078.2/35717This master's thesis conducts empirical research on the estimation via machine learning of the decision parameters of different financial portfolio optimization strategies. Using the cross-validation method, the aim of the dissertation is to see whether the out-of-sample performance of portfolios estimated via machine learning is superior to that of conventional, analytically estimated, with strong statistical assumptions, portfolios.Machine LearningOptimizationCalibrationPortfolioMarkowitzCross-Validationtext::thesis::master thesisthesis:41636