Create Your Own Discover Weekly Playlist for Spotify Using Machine Learning

Joakim Lehn

Malte Loller-Andersen

Half-day workshop - in English

Have you ever wondered how Youtube and Spotify recommends new videos and songs to you? Do you want to know what characterizes the music you listen to? Join us for this workshop where you create your own Spotify playlist based on your own music taste!


In this workshop we will give you an introduction of various algorithms used for clustering and classifying data and introduce feature extraction and the Spotify API. Then we will use Spotify's API to gather metrics of songs in your playlists, and visualize the data found. Next on the menu are four assignments including finding similar playlists and recommending new songs for yourself.


After this session you will have a greater knowledge of several machine learning algorithms for classifying and clustering data, while exploring your own music taste. You will learn how feature extraction influences the results in machine learning projects, and what you need to take into account when setting up your own projects!

Primarily for: Developers

Participant requirements: Computer with some required software (tensorflow and a few more), we also have an ubuntu image that can be used with the required software installed.