The aim of this research is the use of the artificial neural networks models, specifically Multilayer Perceptrons trained by the algorithm known as Backpropagation to estimate the free housing prices. This methodology allows, through the training of the backpropagated nets, to estimate the houses prices on the basis of some variables, related to the houses, which are considered relevant (location, age, surface, quality, ...), overcoming the linear restrictions characteristic of the traditional statistical models used for this objective. The authors purpose is to show the forecasting power of these techniques as well as to suggest a change in the design of databases which have to do with the real estate market in such a way that the generalized use of this procedure is possible.