The main purpose of this study is to understand how the price of housing is formed in the new ( expo) and old town in Lisbon ( traditional neighborhoods). The study focuses on the prices of the apartments that were sold with the assistance of Estate Agents operating in Lisbon in last 3 years, and how the economic crisis can explain the market price. . For the development of the study, we used two different methodologies: Hedonic Pricing Methods (MPH) and Artificial Neural Networks (ANN). ANN are a less traditional econometric technique from the field of Artificial Intelligence, but they are strong competitors with the MPH. In the last two decades, the MPH has been applied to the real estate market in Portugal but, till the present, no single study is known with the ANN. To obtain the best hedonic model, numerous tests were developed, aiming the validation of MPH and also the adequate selection of variables that contribute most to the prices. The tests were performed with the statistical software SPSS, The explanatory variables included in the final model for the price of an apartment were: the floor area (m2), the garage and basement index, the comfort index, the location index and two other variables resulting of interactions, one between the year of sale and the condition of the apartment (whether it is new or used) and the other between the preservation index and the condition of the apartment. With these six explanatory variables, the MPH has achieved an accuracy quite significant when compared with some previous studies.