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 algorithms are increasingly central to creating consumer experiences.
-
•
User researchers play a crucial role in understanding the complexities of human behavior that algorithms must accommodate.
-
•
Personalization in music involves balancing algorithmic recommendations with editorial insights.
-
•
User personas are essential for tailoring music experiences to different listener types.
-
•
Different contexts (like driving or social events) significantly impact how users interact with technology.
-
•
Skipping songs may not uniformly indicate dissatisfaction; user goals vary by persona.
-
•
The integration of mixed methods research enhances the development process for machine learning applications.
-
•
User researchers are increasingly recognized as necessities within machine learning teams.
-
•
There’s a growing demand for user research, reflecting its importance in tech industries today.
-
•
Cross-functional collaboration between user researchers and machine learning engineers leads to better user experiences.
Notable Quotes
"We are slowly embarking in a world where algorithms decide many of our consumer experiences."
"There was an old world where DJs decided what songs we listened to; now, it’s machines."
"User research has to be the backbone of machine learning experiences."
"Skips are not simply bad things; they tell us complex stories about user interaction."
"Human behavior is notoriously complex and needs to inform machine learning models."
"The definition of mixed methods research needs to be reconsidered."
"We have moved to a model where customer testing happens early and often in the process."
"There hasn't been a better time to be a user researcher than now."
"The responsibility we have at Spotify is to provide the best listening experience."
"Good predictions lead to great personalized playlists."
More Videos
"Disability isn't a problem with a person; it's about the systems and environments we create."
Samuel ProulxInvisible barriers: Why accessible service design can’t be an afterthought
December 3, 2024
"Every organization has the opportunity to change and alter its ways."
Victor UdoewaTheme One Intro
March 27, 2023
"How can we from our design discipline find ways to measure our impact without harming our day-to-day work?"
Gonzalo GoyanesDesign ROI: Cover a Little, Get a Lot
September 8, 2022
"Ethical design can impact some harms, but not all."
Alexandra SchmidtWhy Ethics Can't Save Tech
November 18, 2022
"We have to understand what the language of recognition is in our teams."
Jose CoronadoFrom Zero to Hero
September 8, 2022
"All neurodiversity is unique and not one size fits all."
Pippa LomasPaving the Path for Neurodiversity in Design
October 4, 2023
"There’s a need for a fresh set of eyes to challenge current practices in climate tech."
Louis Rosenfeld Matt Jones Olga Khroustaleva Michael Leggett Karol MunozDo you want to work on climate? (Climate UX Discussion Series)
November 15, 2023
"If you don't hire designers, you're still gonna get design. It's just gonna suck."
Jeff GothelfThe Intersection of Lean and Design
January 10, 2019
"We don't know what else is important, but we certainly expect that there will be other things that will come up as you talk about it."
Dave GrayGroup Activity: Making Sense of DesignOps
November 7, 2017
