Quality of service is one of the most important elements in achieving customer satisfaction and company profitability. It can be considered as a composite of various tangible and intangible assets as well as subjective attributes such as safety, comfort and satisfaction, which are difficult to measure directly. The purpose of this research is to offer an alternative method, supported by computers, to quantitatively evaluate services in the hotel industry, by assigning a value to each question of a questionnaire. An advantage of this method is that there is no need for researchers to inadvertently assign weight to the specific question/items because it is done by a suitable mathematical model. This study assessed latent traits of quality of service in 206 Brazilian hotels, which were evaluated. For this purpose, a structured observation method was carried out, that is, mystery shopping, with anonymous evaluators. Furthermore, through item response theory (IRT), a scale to measure quality of service was constructed, in which items and latent features of hotels in the same unit of measurement are positioned. The results indicated where each hotel is positioned on the scale and which items they need to improve in order to be more competitive or achieve excellence. Moreover, this study provides a structured method, through a mathematical model, to enable management staff to measure latent traits of quality of service in hotels. The measurement scale for quality of service can be used to improve services and to meet customer requirements/expectations. This type of quantification can help the hotel industry to pursue excellence in the age of the Fourth Industrial Revolution.