A carregar...
Publicação
The music industry in the streaming age: predicting the success of a song on spotify
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 718.11 KB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
The digitization of information goods has fundamentally changed the consumption patterns of music, such that the music popularity has been redefined in the streaming era. Still, the production of hit music that captures the lion’s share of music consumption remains the central focus of business operations in the music industry. This paper aims at building a machine learning model capable of predicting the success of songs on Spotify. The created dataset contains 14,303 songs some appeared in Spotify's Global Top 200 chart and others never entered in the chart. The problem was approached as a classification task and the best results were obtained by the Random Forest classifier with an F1 score of 85,6% on the validation set.
Descrição
Palavras-chave
Machine learning Economics of digitization