Improving the song discoverability experience in Spotify
Exploring how Spotify can use generative AI and active features to help users discover songs.
ROLE
Product Designer
Personal Project
TIMELINE
April 2025
CONTEXT
Spotify users aren't satisfied with song recommendations
Spotify has over 670 million users worldwide, but many share similar concerns when it comes to Spotify’s algorithm and music discovery experience. It is often difficult to find new music because many discovery features are passive, making the experience feel limited and at times uninspiring.
WHY SHOULD SPOTIFY CARE?
Even Spotify knows that their recommendations can improve. But how?
To maintain and attract users, Spotify needs to improve their music discovery experience. We took a look at Spotify’s research blog and what work is being done in relation to helping users expand their listening behavior.
The answer? Allowing users to refine their recommendations.
SOLUTIONS
A blend of generative AI and active features to discover new songs.
Using our research, we led our own exploration of what "refining recommendations" could look like. After ideating and going down the chopping block with our ideas; we narrowed down on these five.
DESIGN PRINCIPLES – PROCESS WORK
Outlining core themes across our solutions.
Between creating our solutions and finalizing our insights, we listed out design principles to help guide our decision-making and craft.
IDEATION – PROCESS WORK
We ideated experiences and organized them by effort level.
After brainstorming new ways to discover music, we used our design principle on low cost to help us recognize each feature's potential effort level.
EXPLORATIONS
The ideas that didn't quite stick.
We experimented with a number of ways users could discover more music. After various iterations, some of those ideas just didn't make sense to have for users.
Radio Refresh V1.0
These explorations didn’t move forward because they didn’t have the level of flexibility we thought users would need. The interaction experience also became confusing since there was poor visual feedback.
Daylist Vibe Refine
Users found the Vibe Refine feature useful but the use case was very niche. Vibe Refine would occur when users have multiple vibes for a single Daylist experience which may be rare.
Behind the Scenes Widget
We originally explored a Behind the Scenes widget to better connect listeners to broader aspects of a song. However, we though its impact on music discovery would ultimately be limited compared to other features.
✨ Want to learn more? Let's chat!
For a more in-depth look at our design process, feel free to reach out! I'd be happy to share more.
