The Business Problem
Too many choices can overwhelm users. If offered too many options, the user may not buy anything. Streaming services like Spotify have massive catalogs. Identifying the tracks a user might like and recommending the product they might like is crucial for their business.
To solve this business problem we create two playlists using a clusting algorithm, a Popular Playlist, which is then used to identify songs that are similar to a song a user already likes, giving the user a personalized playlist, or recommendations based on the song similarity value created by each of the features of the user input song and each of the features of each of the songs in the Popular Playlist.
Click on the following link to try your hand at the predictive model…