Music danceability

Python · 2023

Machine-learning experiments predicting song danceability from Spotify audio features.

Overview

A data science team project using the Spotify API: we built and compared several ML models to predict a track’s danceability score from audio features, including feature engineering and model evaluation.

Engineering approach

Spotify-derived features are used to compare supervised models and examine their inputs. The target is Spotify’s own danceability estimate, not a universal objective measure of how danceable a song is.

Scope and limitations

Academic or research work, potentially collaborative. It illustrates an engineering method or experiment rather than claiming a commercially deployed product.

Explore the project

Source repository, documentation or official result ↗

Related work: Deez’Nalyzer · System of linear equations calculator