The use of service life prediction tools can allow a more rational management of the maintenance of a building and its components by supporting reduced life cycle costs of constructed assets. A study was conducted to evaluate the degradation of facades of buildings located in Lisbon, Portugal, and in which visual in-situ inspections of 140 stone cladding facades were completed. Based on this information, different models were proposed to describe the degradation of masonry stone-clad buildings and a novel approach to predicting service life was developed. A description is provided for the use of artificial neural networks to predict the service life of stone cladding of the type that is directly adhered to a building substrate. With the use of artificial neural networks an analytical expression was established to estimate the degradation of this type of cladding system. The viability of this method was then compared with other methods used for service life prediction including multiple linear regression and a graphical method. Some of the statistical parameters used to assess the performance of the various methods are described. Of these three methods, those variables that best explain the degradation of stone cladding, are identified: cladding age, distance from the sea, type of finish, and size of the stone plates.