Soil water retention curves are a key constitutive law in order to describe the physical behaviour of an unsaturated soil. Various computational modeling techniques, that formulate retention curve models, are mostly based on existing soil databases, which rarely considers any effect of stress on the soil water retention. Such effects are anyway crucial in the case of swelling soils. The present work illustrates and explores the ability of computational intelligence based genetic programming approach to formulate the mathematical relationship between the water content, in terms of degree of saturation, and two input variables, i.e. net stress and suction for three different soils (sand-kaolin mixture, Gaduk Silt and Firouzkouh clay). The predictions obtained from the proposed models are in good agreement with the experimental data. Further, the parametric and sensitivity analysis conducted validates the robustness of our proposed model by unveiling important parameters and hidden non-linear relationships