< Back
|
12 Sep, 2023
Spotify's success: A master class in personalisation
Adding the extra ‘you’ to your experience.
We all know and love Spotify, using it to play our favourite songs and discover new music that feels curated just for us. While the user interface is simple and intuitive, beneath the surface lies a heavily complex data infrastructure that enables Spotify to connect with its customers like never before.
Personalisation is exactly what it sounds like: it ensures that the content you receive on Spotify is tailored to you based on the audio you love. It’s now regarded as key to the Spotify experience. But this wasn’t always the way.
Born in 2008 as a digital repository for songs already known to users, Spotify has since grown into a platform that facilitates music discovery. Over time, the engineers realised that people enjoy and use the app more when they’re discovering new music and expanding their library. But the challenge was their limited time and capacity to explore. This realisation propelled Spotify's shift to new frontiers.
Personalisation in action
Through personalising the user experience, Spotify became customer-centric. Instead of viewing themselves as a library providing users’ access to music, Spotify instead used this customer insight to create their value proposition: ‘We’re in the business of discovery.” By flipping their proposition from ‘access’ to ‘discovery’ it enabled them to shift gears, unlocking growth and innovation opportunities. Personalisation was about empowering experiences for listeners who didn’t have the time or knowledge to create endless unique playlists for every dinner party or road trip.
How does personalisation actually work?
The short answer is machine learning, a complex code-based system with thousands of inputs, all laddering up to one song recommendation, done faster than the blink of an eye. Spotify uses three key AI technologies to drive its recommendation software:
#1. Collaborative filtering 📊
Analyses and compares user listening patterns to determine common interests and make recommendations about what other songs a user might enjoy.
#2. Natural language processing (NLP) 📰
Analyses text online, such as social media posts, blogs and news articles, to learn about various artists, albums and genres. It then uses this data to recommend songs based on public perception and perceived similarities between artists.
#3. Audio models👂🏼
Perhaps the most complex, this technology analyses the raw data of each song, such as the lyrics, tone, instrumental variances and other characteristics, to learn about and recommend songs to users interested in similar-sounding music. This is a great way for new artists who may not have a large following or online media coverage to gain exposure. This is highly innovative relative to the Certainty Factor (CF) and Natural Language Processing (NLP).
All this is in addition to what Spotify calls its “algotorial” playlists: sets of songs its editors put together to evoke a certain mood or moment, that are also tailored to the individual user.
Balancing engagement and exploration
Most importantly, personalisation isn't about extending app engagement at any cost. Spotify’s approach is to ensure listeners have a ‘fulfilling content diet’.
Oskar Stal, Spotify’s Vice President of Personalisation explains the importance of balance: “If we really wanted to make you stay on the app three more minutes, we would play your favourite song,” Oskar explained. “All we’d ever have to do is play your favourite 20 songs on a loop. But that would mean you’re not discovering anything, and you’d eventually get tired and bored of the audio experience.”
“In fact, there isn’t just one Spotify experience. There’s more like 365 million different experiences—one for each user—that’s deeply personalised to their wants and needs.”
This multidimensional approach underscores Spotify's commitment to delivering an empathetic customer experience, ultimately prioritising long-term satisfaction over fleeting clicks.
To sum things up:
Spotify's journey from a music library to a personalised discovery hub reflects the transformative power of personalisation. Through a nuanced understanding of its users, Spotify creates an ecosystem where exploration and engagement harmonise to form the bedrock of the brands’ success. In today’s landscape, Spotify's strategy serves as a testament to the fact that technology, when harnessed with empathy, can redefine the customer experience in new ways.
