In this project, I explore how machine learning models can be used to predict the popularity of music songs. For my study, I've utilized Spotify data, which includes two sets: one containing music features, and the other external factors concerning artists. Based on this general approach, I sought to identify the subtle interactions between different track shares and relative listener interest. I use these two data sets to analyze patterns and relationships with the highest effect on track success from my machine learning model, in addition to gaining new insights into the inner workings of this popular music.