Skip to content

Instantly share code, notes, and snippets.

@ryanflach

ryanflach/ryan_flach_m2_lightning_talk_outline.md

Created July 12, 2016 18:42
Show Gist options
  • Save ryanflach/0baff2307228e878102bd8897561d777 to your computer and use it in GitHub Desktop.
Save ryanflach/0baff2307228e878102bd8897561d777 to your computer and use it in GitHub Desktop.
Download ZIP
Outline for Turing Mod2 week3 lightning talk
Raw
ryan_flach_m2_lightning_talk_outline.md

Discover Weekly: Machine Learning in Music Curation

What is Discover Weekly

  • Weekly curated playlist of 30 songs
  • Automatically generated and delivered to all Spotify users
  • Free and incredibly popular

What is Machine Learning

  • "Machine learning is the idea that there are generic algorithms that can tell you something interesting about a set of data without you having to write any custom code specific to the problem. Instead of writing code, you feed data to the generic algorithm and it builds its own logic based on the data." - Machine Learning is Fun

Development

  • Echo Nest (acquired by Spotify in 2014) to determine genres
  • Algorithms to analyze audio signal developed by Spotify intern

Basics of How it Works

  • Individual taste profile is generated via use of Spotify
  • Comparison of playlists across the platform
  • Unheard and/or new songs are added to Discover Weekly playlist
  • No human interference

Functionality in More Detail

  • Other users' playlists, weighted based on popularity
  • Your own taste profile, grouped by artists and genres
  • Outliers are accounted for and weighted appropriately
  • Collaborative filtering and natural language processing
  • Collaborative filtering influences analysis of audio signal
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment