The Spotify Audio Features Hit Predictor Dataset (1960-2019)

Datacite citation style:
Farooq Ansari (2020): The Spotify Audio Features Hit Predictor Dataset (1960-2019). Version 1. 4TU.ResearchData. dataset.
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite
This is a dataset consisting of features for tracks fetched using Spotify's Web API. The tracks are labeled '1' or '0' ('Hit' or 'Flop') depending on some criterias of the author. This dataset can be used to make a classification model that predicts whethere a track would be a 'Hit' or not. (Note: The author does not objectively considers a track inferior, bad or a failure if its labeled 'Flop'. 'Flop' here merely implies that it is a track that probably could not be considered popular in the mainstream.) Here's an implementation of this idea in the form of a website that I made. {}
  • 2020-04-06 first online, published, posted
4TU.Centre for Research Data
media types: application/zip, text/csv, text/plain


files (1)