Summary
Millions of listeners around the world use Spotify to listen to audio experiences that are personalized to their taste, yet relevant in the broader cultural context. Spotify is a unique product because unlike many other eyes the first app, a majority of Spotify experience is phenomenological – it happens in listeners’ ears, minds and bodies, after they hit “Play”. Why do people form Meaningful Connections™ with some type of audio content, but not all, and how do we ensure that our ML models respect the nuances of what makes listening to music and podcasts enjoyable? This talk will shed light on such topics and leave the audience with ideas, challenges and possible best practices for using Mixed Methods Research in the age of ML to build delightful product experiences.
Key Insights
-
•
Machine learning has shifted from backend tech to a frontline role shaping consumer experiences like music recommendations.
-
•
Spotify personalizes not just music content but also merchandising and UI elements like playlist covers and home screen layout.
-
•
Music preferences are deeply contextual, changing by time of day, activity, and listener persona.
-
•
The assumption that skipping a song is a purely negative signal is often incorrect; skip behavior varies by user goals and trust.
-
•
Mixed methods research at Spotify combines data science, qualitative user research, and now increasingly machine learning itself.
-
•
Personas such as 'Nick' (curators) and 'Shelley' (casual listeners) help segment skip behaviors and user needs effectively.
-
•
Editorial playlists blend human curation with ML personalization, balancing communal music experience and individual taste.
-
•
Contextual factors, including social and environmental considerations, greatly influence music listening behavior and signal interpretation.
-
•
User mental models around music and playlists differ significantly across personas and impact engagement and skipping.
-
•
User research teams at Spotify have grown significantly, highlighting the rising importance of research in ML-driven product development.
Notable Quotes
"Machine learning used to be backend technology, but now millions of consumer experiences are decided by machines or algorithms."
"These playlists have some element of machines recommending music in addition to editors behind the scenes."
"There’s been a fundamental shift in consumer products in the last five years driven by machine learning."
"Skipping a song is one of the most common user behaviors and is often assumed to be a bad thing."
"We showed that a skip is not a skip — it varies based on listener goals and trust in the playlist."
"Human behavior is complex and machine learning models need to understand those nuances."
"We consider machine learning as the third leg of mixed methods research, alongside data science and user research."
"Music is personal but also cultural and communal, which creates complexity for personalization."
"Personas like Nick and Shelley help us understand different user attitudes towards music listening and skipping."
"There hasn’t been a better time to be a user researcher, especially in machine learning enabled experiences."
Or choose a question:
More Videos
"Management consultants sell solutions to problems, not just research data, which is why they command high fees."
Nicole Aleong Michaela Mora Prayag Narula Brianna SylverWhat UX research can learn from other research practices [Advancing Research Community Workshop Series]
September 14, 2023
"Innovation is very much a team sport."
Laura KleinUnique challenges of innovation in enterprises
April 23, 2020
"Everything is an experiment."
Erin WeigelReal-world lessons to improve your conversion rates
June 26, 2024
"Once we treat AI as intelligence, we face questions about trust, collaboration, and decision making."
Changying (Z) ZhengNavigating Innovation with Integrity
September 25, 2024
"Teams openly said they didn’t know how to ask questions before and discovered research is cool afterwards."
Dagmara KukawkaTiny team, moonshot impact: Democratizing research across continents
March 10, 2026
"Participants are usually very forgiving if you’re not a perfect screen reader as long as you explain what you’re doing."
Elana Chapman Li Wen Huang Divyen Sanganee Annabel WeinerGetting started with accessibility research
February 20, 2025
"When product says no to design, it’s not personal—it’s about prioritization and what’s most urgent right now."
Iain McMaster IHan ChengDesign and Product: from Frenemy to Harmony
November 29, 2023
"If you’re amazing at your job but no one listens to your research or design, does it really have impact?"
Ian SwinsonDesigning and Driving UX Careers
June 8, 2016
"Collecting habit path data in every study over time builds a data set that informs product decisions."
Paula BachImproving Legacy Software: How Much Better Does it Have to Be?
March 11, 2022
Latest Books All books
Dig deeper with the Rosenbot
What human oversight processes are necessary to ensure the accuracy and relevance of AI-enhanced research repositories?
In what ways are synthetic users or virtual personas currently used in research practice?
What steps help build trust and healing in communities affected by historical traumas during engagement?