SlideShare uma empresa Scribd logo
1 de 20
Baixar para ler offline
Personalized Playlists
@
Spotify
Rohan Agrawal
RE-WORK Machine Intelligence Summit
• New York
• Nov 2, 2016
Spotify in Numbers
• Started in 2006, now available in 59
markets
• 100+ Million active users
• 30 Million + tracks
• 20,000 new songs added per day
• 2+ Billion user generated playlists
What to recommend?
Personalization @ Spotify
‣ Features:
• Discover Weekly
• Release Radar
• Discover Page
• Playlist
Recommendations
• Radio
• Concerts
Recommendations …
Focus on track recommendations
‣Discover Weekly
‣Release Radar
Our ML Models seem to be working!
Today, we’ll talk about 3 types of models
‣ Latent Factor Models
‣ Deep Learning Audio models
‣ NLP models (which are also latent factor models …)
Lets start off with Latent Factor Models
“Compact” representation for each user and items(songs): f-dimensional
vectors
Rohan
Track a
.. . . . .
.. . . . .
.. . . . .
.. . . . .
.. . . . .
.. .
.. .
.. .
.. .
. .
...
...
...
...
..
mUsers
Songs
User Vector Matrix: X: (m x f) Song Vector Matrix: Y: (n x f)
If we were to visualize a few Artist Latent Factors
Implicit Feedback (Hu et al. 2008)
‣ If a user u, listens to an item i, dot product of the user vector and
item vector should be as close to 1 as possible.
‣ Also takes into account confidence of a user liking an item i
‣ Solve with Alternating Gradient Descent or Alternating Least
squares.
Logistic Matrix Factorization (Johnson 2014)
‣ Model the probability of a user clicking on an item as the logistic
function.
‣ Maximize the likelihood of observations R, given ….
Recent Advances in MF
‣ Different loss functions (rank loss)
‣ Use of side information (demographics, metadata)
‣ Use of context (where, when)
‣ Deep Learning CF models
Deep Learning on Audio
http://benanne.github.io/2014/08/05/spotify-cnns.html
Document : User Session
Word : Song
NLP Models For Recommendations
Word2Vec (Mikolov et al. 2013)
‣ Each word / track has an input
and output vector
representation.
‣ Output is a vector space with
similar items living close to each
other in cosine distance. (and
awesome vector algebra
property)
Softmax
skipgram
Sequential Data? RNN ?
‣ Output layer is same as word2vec, softmax. Make a prediction of
the next item based on hidden state
‣ Recurrent connection
‣ Learning output weights and b’s for each item
https://erikbern.com/2014/06/28/recurrent-neural-networks-for-collaborative-filtering/
User Representations?
‣ Word2vec can output word / track representation but what about user
representations.
‣ Simple Aggregation (Bag of words) ?
Averaging problems
‣ Doc2Vec ?
Retrain every time there is new user activity
‣ Clustering?
Losing vector addition information
‣ Learn user vector through RNN ?
Another RNN approach
‣ Assume item vectors are fixed
‣ Try to learn the next item vector in the sequence
‣ Long term intents, train RNN to predict longer ahead in the future
Challenges, what lies ahead
Side information in embedding models, remove regional
biases, external genre information, lyrics, Facebook /
Twitter account data, [ cover art, who knows :) ]
Deep Learning
Transfer Learning
Outlier Detection
Thank You!
You can reach me @
Email: rohanag@spotify.com
Twitter: @rohanag
20

Mais conteúdo relacionado

Mais procurados

Interactive Recommender Systems with Netflix and Spotify
Interactive Recommender Systems with Netflix and SpotifyInteractive Recommender Systems with Netflix and Spotify
Interactive Recommender Systems with Netflix and Spotify
Chris Johnson
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
Roelof van Zwol
 
A/B Testing Pitfalls and Lessons Learned at Spotify
A/B Testing Pitfalls and Lessons Learned at SpotifyA/B Testing Pitfalls and Lessons Learned at Spotify
A/B Testing Pitfalls and Lessons Learned at Spotify
Danielle Jabin
 

Mais procurados (20)

Spotify Discover Weekly: The machine learning behind your music recommendations
Spotify Discover Weekly: The machine learning behind your music recommendationsSpotify Discover Weekly: The machine learning behind your music recommendations
Spotify Discover Weekly: The machine learning behind your music recommendations
 
Personalizing the listening experience
Personalizing the listening experiencePersonalizing the listening experience
Personalizing the listening experience
 
Machine learning @ Spotify - Madison Big Data Meetup
Machine learning @ Spotify - Madison Big Data MeetupMachine learning @ Spotify - Madison Big Data Meetup
Machine learning @ Spotify - Madison Big Data Meetup
 
Interactive Recommender Systems with Netflix and Spotify
Interactive Recommender Systems with Netflix and SpotifyInteractive Recommender Systems with Netflix and Spotify
Interactive Recommender Systems with Netflix and Spotify
 
Music Recommendations at Scale with Spark
Music Recommendations at Scale with SparkMusic Recommendations at Scale with Spark
Music Recommendations at Scale with Spark
 
Building Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at SpotifyBuilding Data Pipelines for Music Recommendations at Spotify
Building Data Pipelines for Music Recommendations at Spotify
 
ML+Hadoop at NYC Predictive Analytics
ML+Hadoop at NYC Predictive AnalyticsML+Hadoop at NYC Predictive Analytics
ML+Hadoop at NYC Predictive Analytics
 
Homepage Personalization at Spotify
Homepage Personalization at SpotifyHomepage Personalization at Spotify
Homepage Personalization at Spotify
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
 
Recent advances in deep recommender systems
Recent advances in deep recommender systemsRecent advances in deep recommender systems
Recent advances in deep recommender systems
 
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems -  ACM RecSys 2013 tutorialLearning to Rank for Recommender Systems -  ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systems
 
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
 
Netflix talk at ML Platform meetup Sep 2019
Netflix talk at ML Platform meetup Sep 2019Netflix talk at ML Platform meetup Sep 2019
Netflix talk at ML Platform meetup Sep 2019
 
Time, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsTime, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender Systems
 
Recommender systems using collaborative filtering
Recommender systems using collaborative filteringRecommender systems using collaborative filtering
Recommender systems using collaborative filtering
 
Personalized Page Generation for Browsing Recommendations
Personalized Page Generation for Browsing RecommendationsPersonalized Page Generation for Browsing Recommendations
Personalized Page Generation for Browsing Recommendations
 
A/B Testing Pitfalls and Lessons Learned at Spotify
A/B Testing Pitfalls and Lessons Learned at SpotifyA/B Testing Pitfalls and Lessons Learned at Spotify
A/B Testing Pitfalls and Lessons Learned at Spotify
 
Past, Present & Future of Recommender Systems: An Industry Perspective
Past, Present & Future of Recommender Systems: An Industry PerspectivePast, Present & Future of Recommender Systems: An Industry Perspective
Past, Present & Future of Recommender Systems: An Industry Perspective
 
Personalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep LearningPersonalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep Learning
 

Destaque

INFOGRAFICA Rainbow Methodology
INFOGRAFICA Rainbow MethodologyINFOGRAFICA Rainbow Methodology
INFOGRAFICA Rainbow Methodology
Maria Rita Fiasco
 

Destaque (19)

WhoToFollow @Spotify
WhoToFollow @SpotifyWhoToFollow @Spotify
WhoToFollow @Spotify
 
EL SEGUNDO HOMBRE O POSTRER ADÁN
EL SEGUNDO HOMBRE O POSTRER ADÁNEL SEGUNDO HOMBRE O POSTRER ADÁN
EL SEGUNDO HOMBRE O POSTRER ADÁN
 
Het muzikale netwerk 2.0 & 3.0
Het muzikale netwerk 2.0 & 3.0Het muzikale netwerk 2.0 & 3.0
Het muzikale netwerk 2.0 & 3.0
 
Omi+ maint en
Omi+ maint enOmi+ maint en
Omi+ maint en
 
Presentación1
Presentación1Presentación1
Presentación1
 
INFOGRAFICA Rainbow Methodology
INFOGRAFICA Rainbow MethodologyINFOGRAFICA Rainbow Methodology
INFOGRAFICA Rainbow Methodology
 
TSEM Spring 2017 Mcarthur Class 2
TSEM Spring 2017 Mcarthur Class 2TSEM Spring 2017 Mcarthur Class 2
TSEM Spring 2017 Mcarthur Class 2
 
Digipak and Poster planning
Digipak and Poster planningDigipak and Poster planning
Digipak and Poster planning
 
José Viña - Envejecimiento a nivel celular y orgánico. Envejecer es normal
José Viña - Envejecimiento a nivel celular y orgánico. Envejecer es normalJosé Viña - Envejecimiento a nivel celular y orgánico. Envejecer es normal
José Viña - Envejecimiento a nivel celular y orgánico. Envejecer es normal
 
RELIGIÓN Y REINO
RELIGIÓN Y REINORELIGIÓN Y REINO
RELIGIÓN Y REINO
 
Reproducción sexual y asexual
Reproducción sexual y asexualReproducción sexual y asexual
Reproducción sexual y asexual
 
biaya konsep
biaya konsepbiaya konsep
biaya konsep
 
#AI is About to Reshape the Workplace & Your Organization's #DataStrategy
#AI is About to Reshape the Workplace & Your Organization's #DataStrategy#AI is About to Reshape the Workplace & Your Organization's #DataStrategy
#AI is About to Reshape the Workplace & Your Organization's #DataStrategy
 
Human presence detection based room light controller using pir2.pptx [repaired]
Human presence detection based room light controller using pir2.pptx [repaired]Human presence detection based room light controller using pir2.pptx [repaired]
Human presence detection based room light controller using pir2.pptx [repaired]
 
Approximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetupApproximate nearest neighbor methods and vector models – NYC ML meetup
Approximate nearest neighbor methods and vector models – NYC ML meetup
 
Web技術の現状と将来 (Open Source Conference 2011 Kyoto)
Web技術の現状と将来 (Open Source Conference 2011 Kyoto) Web技術の現状と将来 (Open Source Conference 2011 Kyoto)
Web技術の現状と将来 (Open Source Conference 2011 Kyoto)
 
Io t40systems @ mesa graz april 2016
Io t40systems @ mesa graz april 2016Io t40systems @ mesa graz april 2016
Io t40systems @ mesa graz april 2016
 
How to Build a Recommendation Engine on Spark
How to Build a Recommendation Engine on SparkHow to Build a Recommendation Engine on Spark
How to Build a Recommendation Engine on Spark
 
Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014Music recommendations @ MLConf 2014
Music recommendations @ MLConf 2014
 

Semelhante a Personalized Playlists at Spotify

Media Sharing on Urban Transport
Media Sharing on Urban TransportMedia Sharing on Urban Transport
Media Sharing on Urban Transport
UCL-CS MobiSys
 
Babar: Knowledge Recognition, Extraction and Representation
Babar: Knowledge Recognition, Extraction and RepresentationBabar: Knowledge Recognition, Extraction and Representation
Babar: Knowledge Recognition, Extraction and Representation
Pierre de Lacaze
 

Semelhante a Personalized Playlists at Spotify (20)

A Semantic Multimedia Web (Part 3)
A Semantic Multimedia Web (Part 3)A Semantic Multimedia Web (Part 3)
A Semantic Multimedia Web (Part 3)
 
Big data and machine learning @ Spotify
Big data and machine learning @ SpotifyBig data and machine learning @ Spotify
Big data and machine learning @ Spotify
 
Large-Scale Capture of Producer-Defined Musical Semantics - Ryan Stables (Sem...
Large-Scale Capture of Producer-Defined Musical Semantics - Ryan Stables (Sem...Large-Scale Capture of Producer-Defined Musical Semantics - Ryan Stables (Sem...
Large-Scale Capture of Producer-Defined Musical Semantics - Ryan Stables (Sem...
 
Platforms and the Semantic Web
Platforms and the Semantic WebPlatforms and the Semantic Web
Platforms and the Semantic Web
 
Automatic speech recognition system using deep learning
Automatic speech recognition system using deep learningAutomatic speech recognition system using deep learning
Automatic speech recognition system using deep learning
 
Recommendations 101
Recommendations 101 Recommendations 101
Recommendations 101
 
AI&BigData Lab 2016. Игорь Костюк: Как приручить музыкальную рекомендательную...
AI&BigData Lab 2016. Игорь Костюк: Как приручить музыкальную рекомендательную...AI&BigData Lab 2016. Игорь Костюк: Как приручить музыкальную рекомендательную...
AI&BigData Lab 2016. Игорь Костюк: Как приручить музыкальную рекомендательную...
 
Igor Kostiuk “Как приручить музыкальную рекомендательную систему”
Igor Kostiuk “Как приручить музыкальную рекомендательную систему”Igor Kostiuk “Как приручить музыкальную рекомендательную систему”
Igor Kostiuk “Как приручить музыкальную рекомендательную систему”
 
Can Deep Learning Techniques Improve Entity Linking?
Can Deep Learning Techniques Improve Entity Linking?Can Deep Learning Techniques Improve Entity Linking?
Can Deep Learning Techniques Improve Entity Linking?
 
Media Sharing on Urban Transport
Media Sharing on Urban TransportMedia Sharing on Urban Transport
Media Sharing on Urban Transport
 
Anghami: From Billions Of Streams To Better Recommendations
Anghami: From Billions Of Streams To Better RecommendationsAnghami: From Billions Of Streams To Better Recommendations
Anghami: From Billions Of Streams To Better Recommendations
 
Reaktive Programmierung mit den Reactive Extensions (Rx)
Reaktive Programmierung mit den Reactive Extensions (Rx)Reaktive Programmierung mit den Reactive Extensions (Rx)
Reaktive Programmierung mit den Reactive Extensions (Rx)
 
The Lonesome LOD Cloud
The Lonesome LOD CloudThe Lonesome LOD Cloud
The Lonesome LOD Cloud
 
LINEデリマでのElasticsearchの運用と監視の話
LINEデリマでのElasticsearchの運用と監視の話LINEデリマでのElasticsearchの運用と監視の話
LINEデリマでのElasticsearchの運用と監視の話
 
Music Recommender Systems
Music Recommender SystemsMusic Recommender Systems
Music Recommender Systems
 
Master's Thesis Alessandro Calmanovici
Master's Thesis Alessandro CalmanoviciMaster's Thesis Alessandro Calmanovici
Master's Thesis Alessandro Calmanovici
 
Encoding and Designing for the Swift Poems Project
Encoding and Designing for the Swift Poems ProjectEncoding and Designing for the Swift Poems Project
Encoding and Designing for the Swift Poems Project
 
Doing data science with F#
Doing data science with F#Doing data science with F#
Doing data science with F#
 
Multilevel Audio Descriptors @WWW09 develtrack
Multilevel Audio Descriptors @WWW09 develtrackMultilevel Audio Descriptors @WWW09 develtrack
Multilevel Audio Descriptors @WWW09 develtrack
 
Babar: Knowledge Recognition, Extraction and Representation
Babar: Knowledge Recognition, Extraction and RepresentationBabar: Knowledge Recognition, Extraction and Representation
Babar: Knowledge Recognition, Extraction and Representation
 

Último

Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
MsecMca
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
ssuser89054b
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
Epec Engineered Technologies
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 

Último (20)

Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
 
notes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.pptnotes on Evolution Of Analytic Scalability.ppt
notes on Evolution Of Analytic Scalability.ppt
 
2016EF22_0 solar project report rooftop projects
2016EF22_0 solar project report rooftop projects2016EF22_0 solar project report rooftop projects
2016EF22_0 solar project report rooftop projects
 
Thermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.pptThermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.ppt
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
 
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Palanpur 7001035870 Whatsapp Number, 24/07 Booking
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equation
 
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
 
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
Introduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaIntroduction to Serverless with AWS Lambda
Introduction to Serverless with AWS Lambda
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 

Personalized Playlists at Spotify

  • 1. Personalized Playlists @ Spotify Rohan Agrawal RE-WORK Machine Intelligence Summit • New York • Nov 2, 2016
  • 2. Spotify in Numbers • Started in 2006, now available in 59 markets • 100+ Million active users • 30 Million + tracks • 20,000 new songs added per day • 2+ Billion user generated playlists
  • 4. Personalization @ Spotify ‣ Features: • Discover Weekly • Release Radar • Discover Page • Playlist Recommendations • Radio • Concerts Recommendations …
  • 5. Focus on track recommendations ‣Discover Weekly ‣Release Radar
  • 6. Our ML Models seem to be working!
  • 7. Today, we’ll talk about 3 types of models ‣ Latent Factor Models ‣ Deep Learning Audio models ‣ NLP models (which are also latent factor models …)
  • 8. Lets start off with Latent Factor Models “Compact” representation for each user and items(songs): f-dimensional vectors Rohan Track a .. . . . . .. . . . . .. . . . . .. . . . . .. . . . . .. . .. . .. . .. . . . ... ... ... ... .. mUsers Songs User Vector Matrix: X: (m x f) Song Vector Matrix: Y: (n x f)
  • 9. If we were to visualize a few Artist Latent Factors
  • 10. Implicit Feedback (Hu et al. 2008) ‣ If a user u, listens to an item i, dot product of the user vector and item vector should be as close to 1 as possible. ‣ Also takes into account confidence of a user liking an item i ‣ Solve with Alternating Gradient Descent or Alternating Least squares.
  • 11. Logistic Matrix Factorization (Johnson 2014) ‣ Model the probability of a user clicking on an item as the logistic function. ‣ Maximize the likelihood of observations R, given ….
  • 12. Recent Advances in MF ‣ Different loss functions (rank loss) ‣ Use of side information (demographics, metadata) ‣ Use of context (where, when) ‣ Deep Learning CF models
  • 13. Deep Learning on Audio http://benanne.github.io/2014/08/05/spotify-cnns.html
  • 14. Document : User Session Word : Song NLP Models For Recommendations
  • 15. Word2Vec (Mikolov et al. 2013) ‣ Each word / track has an input and output vector representation. ‣ Output is a vector space with similar items living close to each other in cosine distance. (and awesome vector algebra property) Softmax skipgram
  • 16. Sequential Data? RNN ? ‣ Output layer is same as word2vec, softmax. Make a prediction of the next item based on hidden state ‣ Recurrent connection ‣ Learning output weights and b’s for each item https://erikbern.com/2014/06/28/recurrent-neural-networks-for-collaborative-filtering/
  • 17. User Representations? ‣ Word2vec can output word / track representation but what about user representations. ‣ Simple Aggregation (Bag of words) ? Averaging problems ‣ Doc2Vec ? Retrain every time there is new user activity ‣ Clustering? Losing vector addition information ‣ Learn user vector through RNN ?
  • 18. Another RNN approach ‣ Assume item vectors are fixed ‣ Try to learn the next item vector in the sequence ‣ Long term intents, train RNN to predict longer ahead in the future
  • 19. Challenges, what lies ahead Side information in embedding models, remove regional biases, external genre information, lyrics, Facebook / Twitter account data, [ cover art, who knows :) ] Deep Learning Transfer Learning Outlier Detection
  • 20. Thank You! You can reach me @ Email: rohanag@spotify.com Twitter: @rohanag 20