Music holds a significant position in global culture, as it is one of the world's most important and dynamic cultural forms. With the vast amount of music-related data available on the Web, new opportunities emerge for extracting knowledge and benefiting different music segments. In this work, we perform a data-driven analysis to investigate musical success from a genre-oriented perspective. Specifically, we model both artist and genre success timelines to detect and predict continuous periods with higher impact. We also build success-based genre collaboration networks to detect collaboration profiles directly related to success. Furthermore, we use data mining techniques to uncover exceptional genre patterns in the networks where the success deviates from the average. Our findings show that studying genre collaboration is a powerful way to assess musical success by describing similar behaviors within collaborative songs. Overall, our work contributes to both the academy and the music industry, as we shed light on the underlying factors of the science behind musical success.