The recommendation system is one of the core technologies for implementing personalization services. Recommendation systems in ubiquitous computing environment should have the capability of context-awareness. In this research, we developed a music recommendation system, which we shall call C2 _Music, which utilizes not only the user’s demographics and behavioral patterns but also the user’s context. For a specific user in a specific context, the C2 _Music recommends the music that the similar users listened most in the similar context. In evaluating the performance of C2 _Music using a real world data, it outperforms the comparative system that utilizes the user’s demographics and behavioral patterns only.