In geomechanics, constitutive models, which relate strains to stresses, have particular importance. This research concerns with developing a constitutive model for rock discontinuities. A large number of research works in this area have shed light on the most important aspects of the shear behavior of rock fractures. However, the constitutive models have been mostly developed in form of empirical functions best representing the experimental data by means of mathematical regression techniques. Thus, now there is room to upgrade the classic regression methods to the more robust modeling techniques which better capture the nonlinearity of constitutive response. In this paper, the support vector regression (SVR) enhanced with a search algorithm has been employed to construct a constitutive model for rock fractures. A series of 84 direct shear tests was conducted on concrete and plaster replicas of natural rock fractures under different levels of normal stress. The specimens had also different mechanical and morphological characteristics. The SVR constitutive model was developed based on the shear test data. The proposed model indicates significant superiority in estimating the shear strength and peak shear displacement compared to Barton–Bandis model for rock fractures.