In recent years, recommender systems have witnessed an increased interest from industry and academia. The deployment of such systems in the hotel industry needs to satisfy specific constraints, making the direct application of classical approaches insufficient. There is an inherent complexity to the problem, starting from the decision-making process for selecting accommodations, which is sharply different from the one for acquiring tangible goods, to the multifaceted behavior of travelers, often selecting accommodations based on contextual factors. Travelers recurrently fall into the cold-start status due to the volatility of interests and the change in attitudes depending on the context. In this paper, we propose a context-aware recommender system for hotel recommendation. The system is based on two novel approaches that take into account geography, temporality, and the trips' intent. Our experiments on a realworld dataset show the impact of taking into account contextual data in improving the quality of the recommendation.