Never Run Out of Great Music with Personalized Recommendation System and Deep Learning

Have you recently run out of great music to listen? Machine learning algorithms can help with daily issues too! Acai is an open source project initialised by Berry Labs, is trying to solve the problem of The Tyranny of Choice (a.k.a “Paradox of Choice) to describe the misery of users facing over-abundant choices. In the music area, especially in the age of streaming music, this paradox becomes so significant that it affects every single piece of choice when users try to enjoy music. It’s why this project was born.

Smartphone Headphones

Music recommendation engines are not new to the world. However, most of them are built on music catalog and acoustic fingerprints to generate playlist by similarities on genre, pattern etc. In addition to music data, some solutions leverage social media as well such as celebrities’ posts on Twitter. Adding social media information opens a new window of methodology of determining music preferences. But they are not neutral to the foundation of music appreciation, of which the most important element is the users themselves. The social effects resulted from the social media information lead to bias in music appreciation not only due to the limitation of exposure to music pools – most of the recommended tracks may come from selected lists like Billboard – but also potentially psychological effects such as peer pressure.

Find out more about the project at http://www.acai.berry.ai