What are the determinants of creativity, novelty, and innovation? In this paper I explore this question through an analysis of data from the Song Explorer podcast, where composers describe how they created a specific song. I mine their accounts to classify their processes into seven different, but not mutually exclusive, theories of the creative process. The result of this exercise suggests that the recombination of existing songs is a major process for the creation of new successful songs. The second step uses the average number of daily YouTube views per day since the songs' video release as a measure of the song's impact, and tests how this impact is associated with the seven theories. For each song in the sample, I have one or more other songs which were explicitly indicated as an influence or inspiration. I use the music genre classification system Every Noise at Once, that provides a map of over 1800 genres and millions of songs to create a set of descriptive statistics of the similarity of each song to their inspiration-songs. These statistics are used to measure different recombination strategies in a regression that seeks to explain songs' relative success, while controlling for other determinants, such as the artists' established level of popularity. The results confirm the optimal differentiation hypothesis that the simultaneous presence of conventionality together with novelty, and not just one or the other, is a major determinant of creativity and success.