I'm sure it could work better but I surely don't think that it's dead and I'll never stop using it. But even more than the generated “Daily Mix” and “Weekly Discover” playlists, I’ve found the best way to discover new music on Spotify is through their "Radio" algorithm. Spotify Offering to Boost Artists’ Algorithm Placement in Exchange for Reduced Royalties "Discovery Mode" would potentially elevate a song's appearance within Spotify's Autoplay and Radio features Ignore the Like button. Additionally, for further accuracy, Spotify uses NLP or Natural Language Processing in analyzing the “playlist itself as a document” (Johnson, 2015), using each song title, artist or other textual evidence to analyze as part of their machine learning recommendation algorithm. Specifically, I focus on Implicit Matrix Factorization for Collaborative Filtering, how to implement a small scale version using python, numpy, and scipy, as well as how to scale up to 20 Million users and 24 Million songs using Hadoop and Spark. I categorized the recommendations I received throughout the year into three groups — people I knew personally, media sources like music sites or podcasts, and algorithm-driven playlists in Spotify — to see if once type had unique success. I cross-referenced the data with my streaming history to identify additional patterns and correlations. Spotify’s algorithm is taking note every time people save your music to their queue, library, or their own playlist and also takes into consideration the number of followers you have. Spotify actually makes people into more conservative listeners, a process aided by its algorithms, which steer you towards music similar to your most frequent listening. It is the essential source of information and ideas that make sense of a world in constant transformation. Topics Wired UK Spotify Music algorithms WIRED is where tomorrow is realized. Photo: Aytac Unal/Anadolu Agency/Getty. Spotify’s curation algorithm influences what music the platform’s users hear in a number of ways. Spotify wants you to keep hitting Like on your favorite songs to train its algorithms to your tastes, but I found that resulted in too much of a good thing. I find it quite useful whether it's a playlist radio or song radio, the amount of new songs and bands I've discovered because of it is quite a bit. Spotify is doing everything it can to get you to listen to more music. I love Spotify but it's radio algorithms suck. In this presentation I introduce various Machine Learning methods that we utilize for music recommendations and discovery at Spotify. The company has created algorithms to govern everything from your personal best home screen to curated playlists like Discover Weekly, and continues to experiment with new ways to understand music, and why people listen to one song or genre over another. How complex they design determines accuracy of the system. Spotify’s algorithm is what’s behind this feature and it promises to give users exactly what they want. Basically, for any song, playlist, artist, or album, Spotify can generate a “Radio Station” of similar songs, a la Pandora. All commercial apps out there like Facebook, Google, Amazon, Netflix and Spotify are recommendation systems. The most obvious is the algorithm-based personalised playlists like Discover Weekly.