Creating Human-Centered Algorithms for Music Services
Spotify and Its Ancestor ‘The Music Genome Project’ (Now Pandora)
User Experience (UX) Research is important to how you shape a product for users to use on a daily basis. There are various forms of research that can be done such as qualitative, quantitative and a mix of both methods to help drive the intended goals of a particular product. In this article we are going to focus on how music streaming services such as Spotify, have benefited from early research and algorithm development, such as the music genome project, to shape who they are today.
From Wikipedia:
The Music Genome Project is an effort to “capture the essence of music at the most fundamental level” using over 450 attributes to describe songs and a complex mathematical algorithm to organize them. The Music Genome Project is currently made up of 5 sub-genomes: Pop/Rock, Hip-Hop/Electronica, Jazz, World Music, and Classical. Under the direction of Nolan Gasser and a team of musicological experts, the initial attributes were later refined and extended.
A given song is represented by a vector containing values for approximately 450 “genes” (analogous to trait-determining genes for organisms in the field of genetics). Each gene corresponds to a characteristic of the music, for example, gender of lead vocalist, prevalent use of groove, level of distortion on the electric guitar, type of background vocals, etc. Rock and pop songs have 150 genes, rap songs have 350, and jazz songs have approximately 400. Other genres of music, such as world and classical music, have 300–450[1] genes. The system depends on a sufficient number of genes to render useful results. Each gene is assigned a number between 0 and 5, in half-integer increments.[2] The Music Genome Project’s database is built using a methodology that includes the use of precisely defined terminology, a consistent frame of reference, redundant analysis, and ongoing quality control to ensure that data integrity remains reliably high.[1]
Algorithms are becoming a huge part of our daily lives. They are used in social media platforms, to influence what we watch next on Netflix or even to what we purchase online, all have certain algorithms in place that are used to influence behavior with how we use technology. What algorithms are a particular set of rules or calculations that are put into a particular application in the development process.
The music genome project was a complex algorithm developed to be implemented at TowerRecords.com, a project that HireWisdom Founder Lisa Galarneau helped conceive and execute in the early 2000s. It was designed to change the way customers searched, browsed and purchased music from the site. The way it focused on this was by having:
- Having a well trained musical expert that has four year degree that understands music
- Which then it analyzed artists, tracks, genres and the year using those data points to classify them in a category.
The music genome project algorithm was designed to be one one of its kind. It didn’t rely on purchase history like other algorithms often did, but what people frequently listened to . This algorithm helps benefit the listener because it gives the user the ability to discover new artists based on what a user enjoyed which encourages them to continue to use the platform to discover more. This not only helps artists get discovered but also helps keep the engagement up on the platform. Perhaps even adding more users which adds to the ROI. Currently the music genome project powers the popular music streaming service Pandora.
Spotify is one of the most popular music streaming platforms today. Its attractive user interface (UI) and the price isnt what is making it a super popular platform, it is how the user experience (UX) has taken listening to another level. All this is done because of how algorithms are implemented within the platform. Spotify designed its software to how users listen today. In a recent study I conducted, users often relied on Spotify algorithmic playlists to pick what the users will listen to next. In one way it shaped how we consume music today but also changed users behavior. Since this is specific to each listener each user gets a chance to have their own experience.
In a recent UX Research project that I did, I investigated what drove users to the Spotify music platform. After conducting a field study on how people listen to music, it showed many users focused on allowing the algorithm to choose what they listen to rather than them choosing for themselves. For example, users always frequented the “ New Music Friday” playlist, that playlist was curated based on the artists a particular user frequently listened to.
Algorithms are here to stay, whether it is on our music streaming platforms, sites we visit or what we purchase. Algorithms enhance the UX of a given product in order to achieve certain goals. As in the case for Spotify, their goal was to encourage users to listen to more music based on what they like already.
About The Author:
Abraham (Abe) Bogere is a UX specialist, US Air Force Veteran, and Research Consultant with HireWisdom.org
