SlideShare uma empresa Scribd logo
1 de 26
Baixar para ler offline
Homepage Personalization
at Spotify
Oğuz Semerci, Aloïs Gruson, Clay Gibson, Ben Lacker, Catherine Edwards, Vladan Radosavljevic
Spotify is a global audio
subscription service
By the
numbers
232M
108M
79
50M+ 450k+
What’s at stake on the Homepage?
The Homepage is the first thing you see when you open the app. It
is many things: a discovery tool, a personal music assistant, a
marketplace for artists and their fans.
Spotify’s mission is to unlock the potential of human creativity —
by giving a million creative artists the opportunity to live off their art
and billions of fans the opportunity to enjoy and be inspired by it.
Personalization is powerful in this challenging content space with
vast volume and variety.
01 More on Spotify Homepage
02 Overview of the Ranking algorithm and the bandit policy
03 Sanity checks used in practice for policy debiasing and model behavior
Talk outline
Homepage
organization
The Homepage is made up of cards:
podcast shows or episodes, albums,
playlists, radio stations, artist pages,
etc.
Cards are organized into shelves.
Shelf A
Shelf B
Each user is eligible for hundreds of
candidate shelves, which can be
editorially or programmatically
curated. Shelves pull from a pool of
millions of cards.
All shelf candidates and their
respective cards are ranked in
real-time when you load Home.
Made for X
Your Favorite Albums
Similar to Y
Recommended for Today
Iconic 80s Soundtracks
Discovered in Greenwich Village
Programmatic Curation
Editorial Curation
Embedding
Network
Ranking
Recommendation
Funnel
Ranking Algorithm
and Bandit Policy
Log user feedback:
interactions such as clicks,
likes, streams
Learn to rank Homepage based on logged feedback data.
Homepage ranking as end-to-end ML problem
Ranking algorithm serves
recommendations
Train ranking
algorithm
using logged
feedback
Consequences of Feedback Loops
Without randomization in the feedback loop, you risk:
● Homogenized user behavior (Chaney et al. 2018)
● Diminishing diversity over time (Nguyen et al. 2014)
● Poor representation of the long tail (Mehrotra et al. 2018)
Continuous exploration and content pool expansion
are helpful (Jiang et al, 2019)
Log user feedback:
interactions such as clicks,
likes, streams
Ranking algorithm serves
recommendations
Train ranking
algorithm
using logged
feedback
Introduce exploration
Exploration policy
introduces
randomness
Log user feedback:
interactions such as clicks,
likes, streams
Ranking algorithm serves
recommendations
Train ranking
algorithm
using logged
feedback
+ policy
propensities
Introduce exploration
Random data collection
Randomize the Homepage
for a small fraction of
requests
Ways to introduce exploration
Bandit Policy
Explore/exploit as
Homepage is assembled
(McInerney et al., 2018)
Bandit approaches are becoming popular:
● Artwork personalization at Netflix (Amat et al. 2018)
● News article recommendation in Yahoo (Chu et al. 2012)
● Personalization at Amazon Music (ICML 2019)
● REVEAL ’19 workshop here
Fully randomized
experiment
Randomize the Homepage
for a small fraction of users
Explore/Exploit
on the Homepage
An example of an epsilon-greedy policy for
ranking the Spotify Homepage.
0.7 0.20.8
Card Candidates
Predicted stream rate
Explore/Exploit
on the Homepage
An example of an epsilon-greedy policy for
ranking the Spotify Homepage.
0.7 0.20.8
Card Candidates
0.8
𝜋 = (1- 𝝐) + 𝝐/ 3
Explore/Exploit
on the Homepage
An example of an epsilon-greedy policy for
ranking the Spotify Homepage.
0.7 0.20.8
Card Candidates
0.8 0.2
𝜋 = 𝝐/ 2
Explore/Exploit
on the Homepage
An example of an epsilon-greedy policy for
ranking the Spotify Homepage.
0.7 0.20.8
Card Candidates
0.8 0.2 0.7
𝜋 = 1
Training the reward model*
Counterfactual inference for model parameters
* Explore, Exploit, Explain: Personalizing Explainable Recommendations with Bandits. J McInerney, B Lacker, S Hansen,
K Higley, H.Bouchard, A Gruson & R Mehrotra. RecSys 2018.
Research Directions & Practical Challenges
Many research directions we work on:
● Designing better reward models (REVEAL, talk by Mounia Lalmas)
● Optimizing for the marketplace (Marketplaces tutorial, Rishabh and Ben)
● Careful feature engineering to mitigate feedback loop side effects and better
rank new content
● Creating a more representative Homepage (Henriette Cramer in Responsible
Recommendation Panel)
But we need to have integration tests (kind of) so that we are confident that we’ve
got the basics right.
Sanity Checks
used in Practice
Three examples
Need a way to validate that policy debiasing yields roughly unbiased training data.
Sanity Checks
for policy debiasing
Method:
● Remove position bias by using training data from top
position..
● Train a linear model with a single feature (shelf_name) to
predict a metric that’s observable online (CTR).
● Compare prediction from debiased model to observed
outcome during exploration in that position.
Need a way to validate that policy debiasing yields roughly unbiased training data.
Sanity Checks
for policy debiasing
With
importance
sampling
Without
importance
sampling
Product strategy
Sanity Checks
for problem specific model behavior
Aggregate ranking metrics (e.g. NDCG) have low resolution and offer little visibility into
model behavior. But stakeholders have expectations about what the model should do in
specific situations. We build trust in the model internally and externally by creating metrics
around these expectations and using them as sanity checks.
Artists
Curators
Users
Music has repetitive consumption patterns.
Users have habitual behavior on Home. If a
user has a clear preference for a specific shelf,
models should rank that shelf high on the
page, regardless of what it is.
A user has a “favorite” shelf if a significant
amount of their consumption can be attributed
to that shelf.
Measure the average row where that shelf is
placed for those users.
Favorite Shelf Position Sanity Check
modelA modelB
shelfX
shelfY
shelfZ
Daily & Hourly Patterns Sanity Check
“Why don’t I see “Peaceful Piano” on top of my
homepage every night?”
● Zoom into repetitive consumption patterns and
habitual behavior.
● Measure if the row position is higher at the right
time when applicable.
streamrate
01 Motivation for exploration when collecting training data
02 Methods for collection policies and an epsilon greedy example
03 Three examples of simple sanity checks we use in production while
navigating the complex ecosystem of the homepage personalization
Conclusions
Thank you!
References:
[1] Lihong Li, Wei Chu, John Langford, Robert E. Schapire, A Contextual-Bandit Approach to Personalized News Article Recommendation
arXiv preprint arXiv:1003.0146
[2] Rishabh Mehrotra, James McInerney, Hugues Bouchard, Mounia Lalmas, and Fernando Diaz. 2018. Towards a Fair Marketplace:
Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems. CIKM '18. ACM, New
York, NY, USA, 2243-2251
[3] Allison J. B. Chaney, Brandon Stewart, and Barbara Engelhardt. 2017. How algorithmic confounding in recommendation systems
increases homogeneity and decreases utility. arXiv preprint arXiv:1710.11214
[4] J. McInerney, B. Lacker, S. Hansen, K. Higley, H. Bouchard, A. Gruson, R. Mehrotra. Explore, Exploit, Explain: Personalizing Explainable
Recommendations with Bandits. In ACM Conference on Recommender Systems (RecSys), October 2018
[5] Ray Jiang, Silvia Chiappa, Tor Lattimore, Andras Agyorgy, and Pushmeet Kohli. 2019. Degenerate Feedback Loops in Recommender
Systems. arXiv:arXiv:1902.10730
[6] Thorsten Joachims, Adith Swaminathan, Tobias Schnabel Unbiased learning from biased user feedback arXiv:arXiv:1608.04468
[7] Fernando Amat, Ashok Chandrashekar, Tony Jebara, and Justin Basilico. 2018. Artwork personalization at netflix. In Proceedings of the
12th ACM Conference on Recommender Systems (RecSys '18).
https://www.spotifyjobs.com

Mais conteúdo relacionado

Mais procurados

Recent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveRecent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveJustin Basilico
 
Contextualization at Netflix
Contextualization at NetflixContextualization at Netflix
Contextualization at NetflixLinas Baltrunas
 
Music Personalization At Spotify
Music Personalization At SpotifyMusic Personalization At Spotify
Music Personalization At SpotifyVidhya Murali
 
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 SystemsYves Raimond
 
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 PerspectiveJustin Basilico
 
Engagement, metrics and "recommenders"
Engagement, metrics and "recommenders"Engagement, metrics and "recommenders"
Engagement, metrics and "recommenders"Mounia Lalmas-Roelleke
 
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 2019Faisal Siddiqi
 
Déjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsDéjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsJustin Basilico
 
A Multi-Armed Bandit Framework For Recommendations at Netflix
A Multi-Armed Bandit Framework For Recommendations at NetflixA Multi-Armed Bandit Framework For Recommendations at Netflix
A Multi-Armed Bandit Framework For Recommendations at NetflixJaya Kawale
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at NetflixJustin Basilico
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender SystemsRoelof van Zwol
 
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 LearningAnoop Deoras
 
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
 
Data council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixData council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixGrace T. Huang
 
Algorithmic Music Recommendations at Spotify
Algorithmic Music Recommendations at SpotifyAlgorithmic Music Recommendations at Spotify
Algorithmic Music Recommendations at SpotifyChris Johnson
 
Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Mounia Lalmas-Roelleke
 
Personalized Playlists at Spotify
Personalized Playlists at SpotifyPersonalized Playlists at Spotify
Personalized Playlists at SpotifyRohan Agrawal
 
Missing values in recommender models
Missing values in recommender modelsMissing values in recommender models
Missing values in recommender modelsParmeshwar Khurd
 

Mais procurados (20)

Recent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveRecent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix Perspective
 
Recommending and searching @ Spotify
Recommending and searching @ SpotifyRecommending and searching @ Spotify
Recommending and searching @ Spotify
 
Contextualization at Netflix
Contextualization at NetflixContextualization at Netflix
Contextualization at Netflix
 
Music Personalization At Spotify
Music Personalization At SpotifyMusic Personalization At Spotify
Music Personalization At Spotify
 
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
 
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
 
Engagement, metrics and "recommenders"
Engagement, metrics and "recommenders"Engagement, metrics and "recommenders"
Engagement, metrics and "recommenders"
 
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
 
Déjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsDéjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender Systems
 
A Multi-Armed Bandit Framework For Recommendations at Netflix
A Multi-Armed Bandit Framework For Recommendations at NetflixA Multi-Armed Bandit Framework For Recommendations at Netflix
A Multi-Armed Bandit Framework For Recommendations at Netflix
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at Netflix
 
Search @ Spotify
Search @ Spotify Search @ Spotify
Search @ Spotify
 
Interactive Recommender Systems
Interactive Recommender SystemsInteractive Recommender Systems
Interactive Recommender Systems
 
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
 
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
 
Data council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixData council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at Netflix
 
Algorithmic Music Recommendations at Spotify
Algorithmic Music Recommendations at SpotifyAlgorithmic Music Recommendations at Spotify
Algorithmic Music Recommendations at Spotify
 
Metrics, Engagement & Personalization
Metrics, Engagement & Personalization Metrics, Engagement & Personalization
Metrics, Engagement & Personalization
 
Personalized Playlists at Spotify
Personalized Playlists at SpotifyPersonalized Playlists at Spotify
Personalized Playlists at Spotify
 
Missing values in recommender models
Missing values in recommender modelsMissing values in recommender models
Missing values in recommender models
 

Semelhante a Homepage Personalization at Spotify

Social Media and AI: Don’t forget the users
Social Media and AI: Don’t forget the usersSocial Media and AI: Don’t forget the users
Social Media and AI: Don’t forget the usersMounia Lalmas-Roelleke
 
UX STRAT Online 2021 Presentation by Rina Tambo Jensen
UX STRAT Online 2021 Presentation by Rina Tambo JensenUX STRAT Online 2021 Presentation by Rina Tambo Jensen
UX STRAT Online 2021 Presentation by Rina Tambo JensenUX STRAT
 
Sweeny group think-ias2015
Sweeny group think-ias2015Sweeny group think-ias2015
Sweeny group think-ias2015Marianne Sweeny
 
Approaching Big Data: Lesson Plan
Approaching Big Data: Lesson Plan Approaching Big Data: Lesson Plan
Approaching Big Data: Lesson Plan Bessie Chu
 
Fuzzy Logic Based Recommender System
Fuzzy Logic Based Recommender SystemFuzzy Logic Based Recommender System
Fuzzy Logic Based Recommender SystemRSIS International
 
Using Contextual Information to Understand Searching and Browsing Behavior
Using Contextual Information to Understand Searching and Browsing BehaviorUsing Contextual Information to Understand Searching and Browsing Behavior
Using Contextual Information to Understand Searching and Browsing BehaviorJulia Kiseleva
 
Data science and ethics in fundraising
Data science and ethics in fundraisingData science and ethics in fundraising
Data science and ethics in fundraisingJames Orton
 
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptxSampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx20211a05p7
 
Martin bazley evaluating digital learning resources leicester reduced for upl...
Martin bazley evaluating digital learning resources leicester reduced for upl...Martin bazley evaluating digital learning resources leicester reduced for upl...
Martin bazley evaluating digital learning resources leicester reduced for upl...Martin Bazley
 
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...IRJET- Review on Different Recommendation Techniques for GRS in Online Social...
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...IRJET Journal
 
Impersonal Recommendation system on top of Hadoop
Impersonal Recommendation system on top of HadoopImpersonal Recommendation system on top of Hadoop
Impersonal Recommendation system on top of HadoopKostiantyn Kudriavtsev
 
Mini-training: Personalization & Recommendation Demystified
Mini-training: Personalization & Recommendation DemystifiedMini-training: Personalization & Recommendation Demystified
Mini-training: Personalization & Recommendation DemystifiedBetclic Everest Group Tech Team
 
Designing for Evaluation
Designing for EvaluationDesigning for Evaluation
Designing for EvaluationKelly Page
 
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...Earley Information Science
 
Survey Research In Empirical Software Engineering
Survey Research In Empirical Software EngineeringSurvey Research In Empirical Software Engineering
Survey Research In Empirical Software Engineeringalessio_ferrari
 
Measuring the Quality of Online Service - Jinyoung kim
Measuring the Quality of Online Service - Jinyoung kimMeasuring the Quality of Online Service - Jinyoung kim
Measuring the Quality of Online Service - Jinyoung kimJin Young Kim
 
Tutorial on metrics of user engagement -- Applications to Search & E- commerce
Tutorial on metrics of user engagement -- Applications to Search & E- commerceTutorial on metrics of user engagement -- Applications to Search & E- commerce
Tutorial on metrics of user engagement -- Applications to Search & E- commerceMounia Lalmas-Roelleke
 

Semelhante a Homepage Personalization at Spotify (20)

Social Media and AI: Don’t forget the users
Social Media and AI: Don’t forget the usersSocial Media and AI: Don’t forget the users
Social Media and AI: Don’t forget the users
 
20120140506003
2012014050600320120140506003
20120140506003
 
UX STRAT Online 2021 Presentation by Rina Tambo Jensen
UX STRAT Online 2021 Presentation by Rina Tambo JensenUX STRAT Online 2021 Presentation by Rina Tambo Jensen
UX STRAT Online 2021 Presentation by Rina Tambo Jensen
 
MBA
MBAMBA
MBA
 
Sweeny group think-ias2015
Sweeny group think-ias2015Sweeny group think-ias2015
Sweeny group think-ias2015
 
Approaching Big Data: Lesson Plan
Approaching Big Data: Lesson Plan Approaching Big Data: Lesson Plan
Approaching Big Data: Lesson Plan
 
Fuzzy Logic Based Recommender System
Fuzzy Logic Based Recommender SystemFuzzy Logic Based Recommender System
Fuzzy Logic Based Recommender System
 
Using Contextual Information to Understand Searching and Browsing Behavior
Using Contextual Information to Understand Searching and Browsing BehaviorUsing Contextual Information to Understand Searching and Browsing Behavior
Using Contextual Information to Understand Searching and Browsing Behavior
 
Data science and ethics in fundraising
Data science and ethics in fundraisingData science and ethics in fundraising
Data science and ethics in fundraising
 
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptxSampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
SampleLiteratureReviewTemplate_IVBTechIISEM_MajorProject.pptx
 
Martin bazley evaluating digital learning resources leicester reduced for upl...
Martin bazley evaluating digital learning resources leicester reduced for upl...Martin bazley evaluating digital learning resources leicester reduced for upl...
Martin bazley evaluating digital learning resources leicester reduced for upl...
 
NISO Altmetrics Initiative: A Project Update - Martin Fenner, Technical Lead ...
NISO Altmetrics Initiative: A Project Update - Martin Fenner, Technical Lead ...NISO Altmetrics Initiative: A Project Update - Martin Fenner, Technical Lead ...
NISO Altmetrics Initiative: A Project Update - Martin Fenner, Technical Lead ...
 
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...IRJET- Review on Different Recommendation Techniques for GRS in Online Social...
IRJET- Review on Different Recommendation Techniques for GRS in Online Social...
 
Impersonal Recommendation system on top of Hadoop
Impersonal Recommendation system on top of HadoopImpersonal Recommendation system on top of Hadoop
Impersonal Recommendation system on top of Hadoop
 
Mini-training: Personalization & Recommendation Demystified
Mini-training: Personalization & Recommendation DemystifiedMini-training: Personalization & Recommendation Demystified
Mini-training: Personalization & Recommendation Demystified
 
Designing for Evaluation
Designing for EvaluationDesigning for Evaluation
Designing for Evaluation
 
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...
Meaningful Metrics - Aligning Operational Metrics with Marketing & Customer E...
 
Survey Research In Empirical Software Engineering
Survey Research In Empirical Software EngineeringSurvey Research In Empirical Software Engineering
Survey Research In Empirical Software Engineering
 
Measuring the Quality of Online Service - Jinyoung kim
Measuring the Quality of Online Service - Jinyoung kimMeasuring the Quality of Online Service - Jinyoung kim
Measuring the Quality of Online Service - Jinyoung kim
 
Tutorial on metrics of user engagement -- Applications to Search & E- commerce
Tutorial on metrics of user engagement -- Applications to Search & E- commerceTutorial on metrics of user engagement -- Applications to Search & E- commerce
Tutorial on metrics of user engagement -- Applications to Search & E- commerce
 

Último

convolutional neural network and its applications.pdf
convolutional neural network and its applications.pdfconvolutional neural network and its applications.pdf
convolutional neural network and its applications.pdfSubhamKumar3239
 
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Boston Institute of Analytics
 
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxThe Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxTasha Penwell
 
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Boston Institute of Analytics
 
Decoding Patterns: Customer Churn Prediction Data Analysis Project
Decoding Patterns: Customer Churn Prediction Data Analysis ProjectDecoding Patterns: Customer Churn Prediction Data Analysis Project
Decoding Patterns: Customer Churn Prediction Data Analysis ProjectBoston Institute of Analytics
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 217djon017
 
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxmodul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxaleedritatuxx
 
Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBoston Institute of Analytics
 
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...KarteekMane1
 
Principles and Practices of Data Visualization
Principles and Practices of Data VisualizationPrinciples and Practices of Data Visualization
Principles and Practices of Data VisualizationKianJazayeri1
 
Networking Case Study prepared by teacher.pptx
Networking Case Study prepared by teacher.pptxNetworking Case Study prepared by teacher.pptx
Networking Case Study prepared by teacher.pptxHimangsuNath
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryJeremy Anderson
 
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...Unveiling the Role of Social Media Suspect Investigators in Preventing Online...
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...Milind Agarwal
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsVICTOR MAESTRE RAMIREZ
 
What To Do For World Nature Conservation Day by Slidesgo.pptx
What To Do For World Nature Conservation Day by Slidesgo.pptxWhat To Do For World Nature Conservation Day by Slidesgo.pptx
What To Do For World Nature Conservation Day by Slidesgo.pptxSimranPal17
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxMike Bennett
 
Real-Time AI Streaming - AI Max Princeton
Real-Time AI  Streaming - AI Max PrincetonReal-Time AI  Streaming - AI Max Princeton
Real-Time AI Streaming - AI Max PrincetonTimothy Spann
 
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...Boston Institute of Analytics
 

Último (20)

convolutional neural network and its applications.pdf
convolutional neural network and its applications.pdfconvolutional neural network and its applications.pdf
convolutional neural network and its applications.pdf
 
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
Data Analysis Project Presentation: Unveiling Your Ideal Customer, Bank Custo...
 
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptxThe Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
The Power of Data-Driven Storytelling_ Unveiling the Layers of Insight.pptx
 
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
Data Analysis Project : Targeting the Right Customers, Presentation on Bank M...
 
Decoding Patterns: Customer Churn Prediction Data Analysis Project
Decoding Patterns: Customer Churn Prediction Data Analysis ProjectDecoding Patterns: Customer Churn Prediction Data Analysis Project
Decoding Patterns: Customer Churn Prediction Data Analysis Project
 
Insurance Churn Prediction Data Analysis Project
Insurance Churn Prediction Data Analysis ProjectInsurance Churn Prediction Data Analysis Project
Insurance Churn Prediction Data Analysis Project
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2
 
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptxmodul pembelajaran robotic Workshop _ by Slidesgo.pptx
modul pembelajaran robotic Workshop _ by Slidesgo.pptx
 
Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis ProjectBank Loan Approval Analysis: A Comprehensive Data Analysis Project
Bank Loan Approval Analysis: A Comprehensive Data Analysis Project
 
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...
wepik-insightful-infographics-a-data-visualization-overview-20240401133220kwr...
 
Principles and Practices of Data Visualization
Principles and Practices of Data VisualizationPrinciples and Practices of Data Visualization
Principles and Practices of Data Visualization
 
Networking Case Study prepared by teacher.pptx
Networking Case Study prepared by teacher.pptxNetworking Case Study prepared by teacher.pptx
Networking Case Study prepared by teacher.pptx
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data Story
 
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...Unveiling the Role of Social Media Suspect Investigators in Preventing Online...
Unveiling the Role of Social Media Suspect Investigators in Preventing Online...
 
Advanced Machine Learning for Business Professionals
Advanced Machine Learning for Business ProfessionalsAdvanced Machine Learning for Business Professionals
Advanced Machine Learning for Business Professionals
 
What To Do For World Nature Conservation Day by Slidesgo.pptx
What To Do For World Nature Conservation Day by Slidesgo.pptxWhat To Do For World Nature Conservation Day by Slidesgo.pptx
What To Do For World Nature Conservation Day by Slidesgo.pptx
 
Data Analysis Project: Stroke Prediction
Data Analysis Project: Stroke PredictionData Analysis Project: Stroke Prediction
Data Analysis Project: Stroke Prediction
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptx
 
Real-Time AI Streaming - AI Max Princeton
Real-Time AI  Streaming - AI Max PrincetonReal-Time AI  Streaming - AI Max Princeton
Real-Time AI Streaming - AI Max Princeton
 
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...
Decoding the Heart: Student Presentation on Heart Attack Prediction with Data...
 

Homepage Personalization at Spotify

  • 1. Homepage Personalization at Spotify Oğuz Semerci, Aloïs Gruson, Clay Gibson, Ben Lacker, Catherine Edwards, Vladan Radosavljevic
  • 2. Spotify is a global audio subscription service By the numbers 232M 108M 79 50M+ 450k+
  • 3. What’s at stake on the Homepage? The Homepage is the first thing you see when you open the app. It is many things: a discovery tool, a personal music assistant, a marketplace for artists and their fans. Spotify’s mission is to unlock the potential of human creativity — by giving a million creative artists the opportunity to live off their art and billions of fans the opportunity to enjoy and be inspired by it. Personalization is powerful in this challenging content space with vast volume and variety.
  • 4. 01 More on Spotify Homepage 02 Overview of the Ranking algorithm and the bandit policy 03 Sanity checks used in practice for policy debiasing and model behavior Talk outline
  • 5. Homepage organization The Homepage is made up of cards: podcast shows or episodes, albums, playlists, radio stations, artist pages, etc. Cards are organized into shelves. Shelf A Shelf B
  • 6. Each user is eligible for hundreds of candidate shelves, which can be editorially or programmatically curated. Shelves pull from a pool of millions of cards. All shelf candidates and their respective cards are ranked in real-time when you load Home. Made for X Your Favorite Albums Similar to Y Recommended for Today Iconic 80s Soundtracks Discovered in Greenwich Village Programmatic Curation Editorial Curation Embedding Network Ranking Recommendation Funnel
  • 8. Log user feedback: interactions such as clicks, likes, streams Learn to rank Homepage based on logged feedback data. Homepage ranking as end-to-end ML problem Ranking algorithm serves recommendations Train ranking algorithm using logged feedback
  • 9. Consequences of Feedback Loops Without randomization in the feedback loop, you risk: ● Homogenized user behavior (Chaney et al. 2018) ● Diminishing diversity over time (Nguyen et al. 2014) ● Poor representation of the long tail (Mehrotra et al. 2018) Continuous exploration and content pool expansion are helpful (Jiang et al, 2019)
  • 10. Log user feedback: interactions such as clicks, likes, streams Ranking algorithm serves recommendations Train ranking algorithm using logged feedback Introduce exploration
  • 11. Exploration policy introduces randomness Log user feedback: interactions such as clicks, likes, streams Ranking algorithm serves recommendations Train ranking algorithm using logged feedback + policy propensities Introduce exploration
  • 12. Random data collection Randomize the Homepage for a small fraction of requests Ways to introduce exploration Bandit Policy Explore/exploit as Homepage is assembled (McInerney et al., 2018) Bandit approaches are becoming popular: ● Artwork personalization at Netflix (Amat et al. 2018) ● News article recommendation in Yahoo (Chu et al. 2012) ● Personalization at Amazon Music (ICML 2019) ● REVEAL ’19 workshop here Fully randomized experiment Randomize the Homepage for a small fraction of users
  • 13. Explore/Exploit on the Homepage An example of an epsilon-greedy policy for ranking the Spotify Homepage. 0.7 0.20.8 Card Candidates Predicted stream rate
  • 14. Explore/Exploit on the Homepage An example of an epsilon-greedy policy for ranking the Spotify Homepage. 0.7 0.20.8 Card Candidates 0.8 𝜋 = (1- 𝝐) + 𝝐/ 3
  • 15. Explore/Exploit on the Homepage An example of an epsilon-greedy policy for ranking the Spotify Homepage. 0.7 0.20.8 Card Candidates 0.8 0.2 𝜋 = 𝝐/ 2
  • 16. Explore/Exploit on the Homepage An example of an epsilon-greedy policy for ranking the Spotify Homepage. 0.7 0.20.8 Card Candidates 0.8 0.2 0.7 𝜋 = 1
  • 17. Training the reward model* Counterfactual inference for model parameters * Explore, Exploit, Explain: Personalizing Explainable Recommendations with Bandits. J McInerney, B Lacker, S Hansen, K Higley, H.Bouchard, A Gruson & R Mehrotra. RecSys 2018.
  • 18. Research Directions & Practical Challenges Many research directions we work on: ● Designing better reward models (REVEAL, talk by Mounia Lalmas) ● Optimizing for the marketplace (Marketplaces tutorial, Rishabh and Ben) ● Careful feature engineering to mitigate feedback loop side effects and better rank new content ● Creating a more representative Homepage (Henriette Cramer in Responsible Recommendation Panel) But we need to have integration tests (kind of) so that we are confident that we’ve got the basics right.
  • 19. Sanity Checks used in Practice Three examples
  • 20. Need a way to validate that policy debiasing yields roughly unbiased training data. Sanity Checks for policy debiasing Method: ● Remove position bias by using training data from top position.. ● Train a linear model with a single feature (shelf_name) to predict a metric that’s observable online (CTR). ● Compare prediction from debiased model to observed outcome during exploration in that position.
  • 21. Need a way to validate that policy debiasing yields roughly unbiased training data. Sanity Checks for policy debiasing With importance sampling Without importance sampling
  • 22. Product strategy Sanity Checks for problem specific model behavior Aggregate ranking metrics (e.g. NDCG) have low resolution and offer little visibility into model behavior. But stakeholders have expectations about what the model should do in specific situations. We build trust in the model internally and externally by creating metrics around these expectations and using them as sanity checks. Artists Curators Users
  • 23. Music has repetitive consumption patterns. Users have habitual behavior on Home. If a user has a clear preference for a specific shelf, models should rank that shelf high on the page, regardless of what it is. A user has a “favorite” shelf if a significant amount of their consumption can be attributed to that shelf. Measure the average row where that shelf is placed for those users. Favorite Shelf Position Sanity Check modelA modelB shelfX shelfY shelfZ
  • 24. Daily & Hourly Patterns Sanity Check “Why don’t I see “Peaceful Piano” on top of my homepage every night?” ● Zoom into repetitive consumption patterns and habitual behavior. ● Measure if the row position is higher at the right time when applicable. streamrate
  • 25. 01 Motivation for exploration when collecting training data 02 Methods for collection policies and an epsilon greedy example 03 Three examples of simple sanity checks we use in production while navigating the complex ecosystem of the homepage personalization Conclusions
  • 26. Thank you! References: [1] Lihong Li, Wei Chu, John Langford, Robert E. Schapire, A Contextual-Bandit Approach to Personalized News Article Recommendation arXiv preprint arXiv:1003.0146 [2] Rishabh Mehrotra, James McInerney, Hugues Bouchard, Mounia Lalmas, and Fernando Diaz. 2018. Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems. CIKM '18. ACM, New York, NY, USA, 2243-2251 [3] Allison J. B. Chaney, Brandon Stewart, and Barbara Engelhardt. 2017. How algorithmic confounding in recommendation systems increases homogeneity and decreases utility. arXiv preprint arXiv:1710.11214 [4] J. McInerney, B. Lacker, S. Hansen, K. Higley, H. Bouchard, A. Gruson, R. Mehrotra. Explore, Exploit, Explain: Personalizing Explainable Recommendations with Bandits. In ACM Conference on Recommender Systems (RecSys), October 2018 [5] Ray Jiang, Silvia Chiappa, Tor Lattimore, Andras Agyorgy, and Pushmeet Kohli. 2019. Degenerate Feedback Loops in Recommender Systems. arXiv:arXiv:1902.10730 [6] Thorsten Joachims, Adith Swaminathan, Tobias Schnabel Unbiased learning from biased user feedback arXiv:arXiv:1608.04468 [7] Fernando Amat, Ashok Chandrashekar, Tony Jebara, and Justin Basilico. 2018. Artwork personalization at netflix. In Proceedings of the 12th ACM Conference on Recommender Systems (RecSys '18). https://www.spotifyjobs.com