Like many other developed cities, Hong Kong has been suffering from acute problems of urban decay. To solve this building crisis, knowledge of the condition profi le of all buildings in Hong Kong is vital. A territory-wide evaluation of building conditions is required for providing valuable information to public organisations to prioritise action areas and facilitate resource allocation. Through such an exercise, the inherent problem of information asymmetry in building conditions can be resolved by means of screening or labelling. Buildings in better condition will be rewarded with a premium in property price, and this can foster a culture of building care through market forces. Assessing the performance of the whole stock of buildings in the city, however, can be a lengthy and costly process. In this light, this study proposed a practical but justifi able alternative for jump-starting the process. In the proposal, exogenous factors that could explain the variations in building conditions are explored using actual assessment information, and these determinants are used to estimate the conditions of other buildings without the need of actual assessments. The empirical fi ndings show that this proposed estimation algorithm works and has a number of practical and policy implications.