How Spotify Knows What You Want to Hear

The BaRT Algorithm Explained

Have you ever wondered how Spotify knows what music you want to hear? And what do you think of the Daily Mixes? Six personalized lists sorted by genre. All you have to do is choose a list that suits your mood. How does Spotify make these lists? And how does it hit the right chord so often?

Meet BaRT

Meet BaRT, the Spotify algorithm. The brains behind music suggestions. BaRT stands for “Recommendations as Treatments. The purpose of BaRT is to help you find music you’re likely to like. And the better the algorithm is at its job, the more likely you are to keep using Spotify. To make this personalized experience possible, BaRT uses a lot of data. Data from music, data from you and data from other customers.

What Can BaRT Do?

Three systems affect BaRT’s music suggestions: audio analysis, collaborative filtering, and Natural Language Processing. How these systems relate to each other no one knows.

1. Audio Analysis

The simplest part of the Spotify algorithm is audio analysis. BaRT looks at the different musical characteristics of the songs you are listening to. For example, what is the tempo, what instruments are in the music, how danceable is the song? By comparing these statistics, BaRT can find a pattern and recommend similar music. In this way, specific playlists can also be created with only upbeat songs or relaxing songs. This is ideal if, like me, you have diverse music tastes.

2. Collaborative Filtering

The second system is called collaborative filtering. The algorithm analyzes the behavior of other users who like similar music. What kind of songs do other people like? Are there any new songs you don’t know yet? By looking at what other people like, BaRT tries to find music that you are likely to like, too. So basically, Spotify users indirectly help each other in their search for good music.

3. Natural Language Processing

The BaRT algorithm “understands” language through natural language processing. It can analyze lyrics and the language in which the song is written. And just like Google, BaRT can crawl the Web. With its ability to process language, it can read what people on the Internet are saying about music. BaRT looks at blog posts, news articles and social media to see what people are writing about certain artists or songs. Do some artists work together? Did a particular song get a lot of publicity? BaRT uses this information to find new deals and promote popular music.

Do you Have Influence?

In addition to the three factors listed above, you yourself can influence what BaRT will recommend. After all, your behavior has a lot of impact. What numbers do you skip? Which songs do you save? How often do you repeat a particular song? But also: which artists do you follow? And it goes even further. Spotify tracks how long you look at an artist page or an album, for example. After processing this information, BaRT quickly analyzes your behavior and the behavior of people with similar music tastes to then recommend a song you can’t say no to.

Final Thoughts

You may be puzzled by the different types of systems and data processing methods of the Spotify algorithm. But BaRT does what it’s supposed to do: provide you with a unique music experience. Personally, I love that you get new music suggestions and you can choose a music list based on mood. And when you don’t like a song, you can easily skip it or switch to your own Spotify lists. The beauty is that BaRT learns as you change your behavior. If you choose different songs, BaRT will notice and probably integrate it into your new Daily Mixes.

Want to Know More?

Want to read, watch or listen more about this topic? Then check out the links below.