Delve into the world of "Spotify Songs Clustering based on Audio Features," a comprehensive endeavor encompassing code, a research paper, dataset, and presentation slides (check out the github for more info). The project's core aim is to leverage audio features to analyze and cluster songs within the Spotify music library, revealing meaningful patterns and connections within the musical landscape.

Introduction:

This project revolves around harnessing the potential of Spotify API's audio features to effectively cluster songs. By utilizing advanced clustering algorithms on the provided dataset, cohesive groups of songs can be identified, sharing attributes like tempo, energy, danceability, and more. This analytical approach provides valuable insights into the intricate relationships that exist between musical genres, artist styles, and listener preferences.

Dataset Overview:

The project features a meticulously curated CSV dataset, encompassing a diverse array of songs spanning various genres. Each song is enriched with annotated audio features extracted from Spotify's expansive collection. These audio features, coupled with song metadata, lay the groundwork for a comprehensive analysis.

Results Display:

This project epitomizes the exploration into the rich world of music data analysis and clustering, offering a glimpse into the intriguing connections that bind melodies, genres, and audience inclinations.