Scribd
Upload
9 views

jacobson2016

Uploaded by

vidushi14027
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views

jacobson2016

Uploaded by

vidushi14027
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Music Personalization at Spotify

[Abstract for Industrial Session]


Kurt Jacobson Vidhya Murali Edward Newett
Spotify Spotify Spotify
48 Grove St Suite 306 45 W 18th st 45 W 18th st
Somerville, MA 02144 NY, NY 10011 NY, NY 10011
[email protected] [email protected] [email protected]
Brian Whitman Romain Yon
Spotify Spotify
45 W 18th st 45 W 18th st
NY, NY 10011 NY, NY 10011
[email protected] [email protected]

ABSTRACT the challenges and opportunities the system faces a year


Spotify is the world’s largest on-demand music streaming after its launch. We’ll also discuss Spotify’s home page,
company, with over 75 million active listeners choosing what seen by each of our users, currently undergoing vast efforts
to listen to among tens of millions songs. Discovery and around personalization to ensure each listener gets a tar-
personalization is a key part of the experience and critical geted list of playlists, shows and music to select through-
to the success of the creator and consumer ecosystem. In out their day. We’ll discuss the various similarity metrics,
this talk, we’ll discuss the state of our current discovery ap- ranking approaches and user modeling we’re working on to
proaches, such as the Discover Weekly playlist that has al- increase precision and optimize for our users’ happiness.
ready streamed billions of new discoveries and Fresh Finds,
a scalable platform for brand new music that focuses sug- 1. PRESENTER BIO
gestions on the long end of the popularity tail. We’ll discuss
the technologies at scale necessary to distill the informa- 1.1 Vidhya Murali
tion about music from our listeners and the world at large Vidhya is an engineer at Spotify’s Music Recommenda-
we collect outside of Spotify – with the massive amounts of tions team. With domain interests in big data and machine
user-item activity data we collect every day to create highly learning and a passion for building products, Vidhya works
personalized music experiences. on music recommendations and personalization at Spotify.
Entire teams at Spotify focus on understanding both the She works on building scalable data pipelines and machine
creator and listener through collaborative filtering, machine learning models to power users discover their next favorite
learning, DSP and NLP approaches – we crawl the web for music. She received her Masters in Computer Science from
artist information, scan each note in every one of our millions the University of Wisconsin-Madison and Bachelors from
of songs for acoustic signals, and model users’ taste through BITS Pilani, India. She has presented at various confer-
a cluster analysis and in a latent space based on their his- ences including the GHC, WiML and DataEngConf.
torical and real-time listening patterns. The data generated
by these analyses have ensured our discovery products are
precise and help our users enjoy music and media across our
entire catalog.
We’ll dive deep into the workings of Discover Weekly,
our marquee personalized playlist which updates weekly and
reached 1 billion streams within the first 10 weeks from its
release. The technology behind Discover Weekly is powered
by a scalable factor analysis of Spotify’s over two billion
user-generated playlists matched to each user’s current lis-
tening behavior. We’ll discuss its innovative genesis and

Permission to make digital or hard copies of part or all of this work for personal or
classroom use is granted without fee provided that copies are not made or distributed
for profit or commercial advantage and that copies bear this notice and the full citation
on the first page. Copyrights for third-party components of this work must be honored.
For all other uses, contact the owner/author(s).
RecSys ’16 September 15-19, 2016, Boston , MA, USA
c 2016 Copyright held by the owner/author(s).
ACM ISBN 978-1-4503-4035-9/16/09. . . $15.00
DOI: http://dx.doi.org/10.1145/2959100.2959120

373

You might also like