The home screen of the Spotify app is a prime example of how algorithms govern a listening experience. Its goal is to quickly help users find something they are going to enjoy listening to, according to a presentation by Spotify Research director Mounia Lalmas-Roelleke at the Web Conference earlier this year. Mar 02, 2019 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.
Research
Analyzing Secondary Data
To begin, I conducted a rapid research session of secondary sources. I spent a few hours getting a sense of Spotify’s place within the landscape of streaming music providers and gathering enough information to help determine the focus and scope of my research. I identified some key challenges and opportunities and made a list of initial assumptions and questions. From there, I conducted a competitive analysis comparing competitors’ strengths and weaknesses, as well as identifying where opportunities for Spotify to differentiate itself with a social feature might exist.
App Audit
In my research, I found that Millennial’s comprise 72% of Spotify listeners and are also listed as top smartphone users, with a 98% ownership rate. Based on this information, I made the initial assumption that Spotify’s users might prefer to connect and communicate socially through Spotify via the mobile app.
Although extremely familiar with the mobile app, I thought it was important to conduct an app audit. This helped me gain a clear grasp of the app’s architecture, hierarchy and content, which I felt was important to establish before considering how a new feature might integrate within the design. Provisional Personas
I then created three provisional personas Spotify widget android app. based on key demographics and behavioral traits of Spotify users. These personas helped me frame my interview planning and identify ideal interview subjects.
Free spotify account on sonos. Conducting Primary Research
Drawing from the list of questions and assumptions I drafted during my secondary research and research plan, I crafted questions to ask participants about their music listening and sharing habits. I interviewed 5 people in person at a local coworking / coffee shop. Participants ranged in age from early 20’s to mid 30's, resided in major US cities, and reported listening to music daily. View Interview Guide
Spotify Recommendation (Matching) Algorithm
As an avid music listener and dedicated scourer of music blogs, news sites, etc. to find new music, one matching mechanism that I constantly use in my life is Spotify’s Discover Weekly system. Descargar app spotify premium gratis. Each week Spotify aggregates a collection of songs they think you’d enjoy into a neatly organized playlist based on a multitude of factors. Prior to this class, I never thought too much of it and just assumed that the songs were chosen based on what songs I’d listen to the week prior and using Shazam’s system of music recognition or what other songs users who listened to the same song listened to. However, after learning about matching my curiosity peaked and I chose to find out exactly how this godsend works.
Spotify isn’t unique in their music recommendation as most other music streaming sites like Pandora, Soundcloud, etc. have similar algorithms, however Spotify’s is unique in that it has a much more complex algorithm which takes more factors into account. For example, Pandora’s recommendation algorithm recommends songs almost solely on the binary ranking (thumbs up=like or thumbs down=don’t like) that you’ve given songs before and based on those adjust its recommendation accordingly. Spotify, however, combines numerous factors in its decision to recommend and group certain songs. For one, it analyzes playlists that other users have created and, based on songs you’ve already listened to repeatedly or saved to your library, suggests songs frequently grouped with it. For example, if a playlist contains 7 of your favorite songs, Spotify would recommend another song in that same playlist considering you and the playlist’s creator share similar tastes. Spotify premium free apk mod. Secondly, the algorithm takes your “taste profile” into account. Your “taste profile” uses music analytics to break down your music taste into the most niche of musical subgenres to make the most accurate suggestions in the future. Finally, the last ingredient is Spotify’s version of Google’s PageRank algorithm that we learned about in Networks I. Similarly to how Google used clicks as votes, this algorithm analyzes a user’s personal use of a song from the Discover Weekly playlist of the week(s) prior to see what songs the user likes to hear that song alongside and uses what songs they incorporated from Discover Weekly as votes. Then by analyzing the user’s personal playlist and seeing how they group songs together the Spotify algorithm computes these 3 main factors (along with a few less significant factors) to suggest new songs. The beauty of the algorithm is that it isn’t stringent and adapts to each week and shift in the user’s streaming history to suggest songs that might fit the user’s current mindset. While not necessarily the traditional matching model of strict preferences and matching to single items, Spotify’s algorithm shows how a complex network of users and their individual preferences can be used to match others to similar data.
Song Suggestions Spotify
Sources: http://qz.com/571007/the-magic-that-makes-spotifys-discover-weekly-playlists-so-damn-good/
CommentsLeave a Reply
You must be logged in to post a comment.
Recently WrittenSpotify App Suggestion Algorithm SoftwareMonthly Archives![]() Spotify App Suggestion Algorithm TemplateBlogrollComments are closed.
|
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |