Data Analytics on
Spotify Music Tracks
Objective
The goal of this project is to identify the key audio and metadata features that influence a song’s popularity on Spotify, and to build models that can predict the popularity score of a track (on a scale from 0 to 100).
Dataset
Source: Spotify Tracks Dataset via Kaggle
Volum: 120,000 rows, 21 columns
The dataset contains 114,000+ songs with metadata and audio features extracted from Spotify’s Web API.
Features & Target
Track metadata: Name, artist(s), album, genre, explicit content flag.
Audio features: Danceability, energy, loudness, valence, tempo, acousticness, speechiness, instrumentalness, and more.
Target variable: popularity (0–100), reflecting how frequently and recently the track has been played.