SlideShare a Scribd company logo
1 of 29
Download to read offline
May 6th, 2014
Real-Time Personalization
with Ad Tech @Spotify
Kinshuk Mishra
kinshuk@spotify.com
@_kinshukmishra
1
About Me
• @Spotify since 2011
• Data and Backend engineering
• With the Monetization team
May 12, 2014
Spotify in numbers
Started in 2006, available in 56 markets
20+ million songs, 20,000 added daily
24+ million active users, 6+ million subscribers
1.5 billion playlists
May 12, 2014
Monetization at Spotify
• $1 billion paid to rights holders since launch
• 1 in every 4 Spotify users is a paying subscriber
• Ad revenue pays for free tier music streaming
• Build platform to power artist and music label promotions
What is our mission?
• Power the free tier with ads customers love.
– Delight users, brands and artists with standout
promotional experiences.
– Deliver the right message for every moment.
5
Delight users, brands and artists with standout
promotional experience
6
• Ad formats need to be
- Native
- Actionable
- Scalable
- Engaging
7
Spotlight
8
Album promotion
9
Sponsored Genre
10
Sponsored Genre
11
!(Right message for every moment)
Things we had to do
• Make ads context aware.
• Create measurable ad formats.
• Build tools to help brands understand their audience.
• Build flexible targeting infrastructure.
• Analyze user behavior to improve ad relevancy.
12
Why is real time interesting?
• True assessment of the context
- current view, last track, etc.
• Immediate feedback
- ad clicked, followed a playlist, etc.
• Increased ad opportunities
- hyperlocal, current mood, etc.
13
source : http://nativemobile.com/tag/real-time-bidding
How to serve right message for every moment ?
• Fix the WTFs for ads in the music context
- Realtime short window activity analysis
• Improve ad relevancy based on user behavior
- (Realtime + Batch) long window activity analysis
14
Some quick wins
• Fix the WTFs for ads in the music context
- Fix the “Not Safe For Kids” ads problem.
- Fix the relevancy of ads in your music session.
• Improve ad relevancy based on user behavior
- Fix ad relevancy based on user’s musical taste.
15
Targeting Architecture
16
Desired overall design
17
Our requirements
• Scalable log collection
• Capability to process logs in batch and
realtime mode and aggregate user activity
• Capability to store user profiles and
enable serve time lookups
• Ability to update and add new features to
existing user profiles
Bigdata @Spotify and choices
• 700 node hadoop cluster
• 400 GB service logs daily
• 4.5 TB user data daily
• 7500 hadoop jobs daily
• 64 TB data generated daily
• YARN Map-Reduce, Giraph,
Storm, Spark, etc. 
!
19
Overall design and tech choices
20
Source : http://tfosuccess.com/day-106-107-the-storm-arrived/
What is Storm?
• Real time stream processing
• Like Hadoop without HDFS
• Like Map/Reduce with many reducer steps
• Fault tolerant and guaranteed message processing
21
Storm @Spotify
• storm-0.8.0
• 22 node cluster
• 15+ topologies
• 200k tuples/second
• ads, recommendation,
analytics, monitoring, etc.
22
source: http://storm.incubator.apache.org/
Use-case
Use real-time session genre information to control 
ad serving in real-time
23
Realtime activity analysis
• Kafka -> Storm -> Memcached -> Targeting Backend
• Soft realtime
• Easy to scale
24
Getting data
25
Getting data across the globe
26
Genre Topology
27
May 12, 2014
Measuring effectiveness
• Build ad quality scores from lower-level metrics
• Positive response, avoidance, etc.
• A/B test hypotheses, evaluate against quality scores 
• Build quality score optimization into real-time system
May 6th, 2014
Want to join the band?
https://www.spotify.com/us/jobs/ or
https://twitter.com/Spotifyjobs
!
Kinshuk Mishra 
kinshuk@spotify.com @_kinshukmishra

More Related Content

What's hot

Building a relevance platform with Couchbase and Elasticsearch
Building a relevance platform with Couchbase and ElasticsearchBuilding a relevance platform with Couchbase and Elasticsearch
Building a relevance platform with Couchbase and ElasticsearchJeroen Reijn
 
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...confluent
 
Memrise presentation @ London Snowplow meetup
Memrise presentation @ London Snowplow meetup Memrise presentation @ London Snowplow meetup
Memrise presentation @ London Snowplow meetup idan_by
 
Hippo CMS Integration Patterns
Hippo CMS Integration PatternsHippo CMS Integration Patterns
Hippo CMS Integration PatternsJeroen Reijn
 
Hippo GetTogether: The architecture behind Hippos relevance platform
Hippo GetTogether: The architecture behind Hippos relevance platformHippo GetTogether: The architecture behind Hippos relevance platform
Hippo GetTogether: The architecture behind Hippos relevance platformJeroen Reijn
 
Real-time visitor analysis with Couchbase and Elastichsearch
Real-time visitor analysis with Couchbase and ElastichsearchReal-time visitor analysis with Couchbase and Elastichsearch
Real-time visitor analysis with Couchbase and ElastichsearchJeroen Reijn
 

What's hot (6)

Building a relevance platform with Couchbase and Elasticsearch
Building a relevance platform with Couchbase and ElasticsearchBuilding a relevance platform with Couchbase and Elasticsearch
Building a relevance platform with Couchbase and Elasticsearch
 
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...
Kafka, the "DialTone for Data": Building a self-service, scalable, streaming ...
 
Memrise presentation @ London Snowplow meetup
Memrise presentation @ London Snowplow meetup Memrise presentation @ London Snowplow meetup
Memrise presentation @ London Snowplow meetup
 
Hippo CMS Integration Patterns
Hippo CMS Integration PatternsHippo CMS Integration Patterns
Hippo CMS Integration Patterns
 
Hippo GetTogether: The architecture behind Hippos relevance platform
Hippo GetTogether: The architecture behind Hippos relevance platformHippo GetTogether: The architecture behind Hippos relevance platform
Hippo GetTogether: The architecture behind Hippos relevance platform
 
Real-time visitor analysis with Couchbase and Elastichsearch
Real-time visitor analysis with Couchbase and ElastichsearchReal-time visitor analysis with Couchbase and Elastichsearch
Real-time visitor analysis with Couchbase and Elastichsearch
 

Similar to Real time ads personalization @ Spotify

Boom Boxes - Android App Marketing Plan
Boom Boxes - Android App Marketing PlanBoom Boxes - Android App Marketing Plan
Boom Boxes - Android App Marketing PlanVarshit Kumar
 
Vinylmint's Growth Strategy Story
Vinylmint's Growth Strategy StoryVinylmint's Growth Strategy Story
Vinylmint's Growth Strategy StoryByron Morgan
 
Spotify: Dominating Music In Real Time
Spotify: Dominating Music In Real TimeSpotify: Dominating Music In Real Time
Spotify: Dominating Music In Real TimeLHBS
 
Making Mobile Work For You, SIPA 2012 Washington DC
Making Mobile Work For You, SIPA 2012 Washington DCMaking Mobile Work For You, SIPA 2012 Washington DC
Making Mobile Work For You, SIPA 2012 Washington DCMary Kay Jerige Lofurno
 
Opportunity with audio
Opportunity with audioOpportunity with audio
Opportunity with audioJunda Ong
 
First Beat Media - Tehnologije na velikim projektima #tnt3
First Beat Media - Tehnologije na velikim projektima #tnt3First Beat Media - Tehnologije na velikim projektima #tnt3
First Beat Media - Tehnologije na velikim projektima #tnt3SICEF
 
Mobile Roadie - Profile Accelerator
Mobile Roadie - Profile AcceleratorMobile Roadie - Profile Accelerator
Mobile Roadie - Profile AcceleratorMobile Roadie
 
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...AIST
 
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentation
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentationOpera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentation
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentationOpera Mobile Store
 
Open Source as a Viable Business Model
Open Source as a Viable Business ModelOpen Source as a Viable Business Model
Open Source as a Viable Business ModelTien-Soon Law
 
Product Owner presentation for Spotify
Product Owner presentation for SpotifyProduct Owner presentation for Spotify
Product Owner presentation for Spotifypdicorpo
 
PMI Project 3- Spotify
PMI Project 3- SpotifyPMI Project 3- Spotify
PMI Project 3- SpotifyTed Shaw
 
Yeovil Stand out on Social Media 6 October 2015
Yeovil Stand out on Social Media 6 October 2015Yeovil Stand out on Social Media 6 October 2015
Yeovil Stand out on Social Media 6 October 2015Get up to Speed
 
The Performance Content Framework
The Performance Content FrameworkThe Performance Content Framework
The Performance Content FrameworkPerformics EMEA
 
Print for Profit - Digital for Growth
Print for Profit - Digital for GrowthPrint for Profit - Digital for Growth
Print for Profit - Digital for GrowthRhapsody
 
ATAK Interactive Marketing Success Stories
ATAK Interactive Marketing Success StoriesATAK Interactive Marketing Success Stories
ATAK Interactive Marketing Success StoriesATAK Interactive, Inc
 

Similar to Real time ads personalization @ Spotify (20)

Boom Boxes - Android App Marketing Plan
Boom Boxes - Android App Marketing PlanBoom Boxes - Android App Marketing Plan
Boom Boxes - Android App Marketing Plan
 
Vinylmint's Growth Strategy Story
Vinylmint's Growth Strategy StoryVinylmint's Growth Strategy Story
Vinylmint's Growth Strategy Story
 
Spotify: Dominating Music In Real Time
Spotify: Dominating Music In Real TimeSpotify: Dominating Music In Real Time
Spotify: Dominating Music In Real Time
 
Data at Spotify
Data at SpotifyData at Spotify
Data at Spotify
 
Making Mobile Work For You, SIPA 2012 Washington DC
Making Mobile Work For You, SIPA 2012 Washington DCMaking Mobile Work For You, SIPA 2012 Washington DC
Making Mobile Work For You, SIPA 2012 Washington DC
 
Dailyhunt Media Deck - June 19'
Dailyhunt Media Deck - June 19'Dailyhunt Media Deck - June 19'
Dailyhunt Media Deck - June 19'
 
Opportunity with audio
Opportunity with audioOpportunity with audio
Opportunity with audio
 
First Beat Media - Tehnologije na velikim projektima #tnt3
First Beat Media - Tehnologije na velikim projektima #tnt3First Beat Media - Tehnologije na velikim projektima #tnt3
First Beat Media - Tehnologije na velikim projektima #tnt3
 
Mobile Roadie - Profile Accelerator
Mobile Roadie - Profile AcceleratorMobile Roadie - Profile Accelerator
Mobile Roadie - Profile Accelerator
 
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...
Dmitry Bugaychenko - Smart.Data@ОК.ru. How to make the world a bit better usi...
 
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentation
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentationOpera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentation
Opera Mediaworks — Mobile Marketing & Advertising Services — 2014 presentation
 
Music 4.5 Iast.fm
Music 4.5 Iast.fmMusic 4.5 Iast.fm
Music 4.5 Iast.fm
 
Open Source as a Viable Business Model
Open Source as a Viable Business ModelOpen Source as a Viable Business Model
Open Source as a Viable Business Model
 
Product Owner presentation for Spotify
Product Owner presentation for SpotifyProduct Owner presentation for Spotify
Product Owner presentation for Spotify
 
PMI Project 3- Spotify
PMI Project 3- SpotifyPMI Project 3- Spotify
PMI Project 3- Spotify
 
POP System 6 - An Introduction
POP System 6 - An IntroductionPOP System 6 - An Introduction
POP System 6 - An Introduction
 
Yeovil Stand out on Social Media 6 October 2015
Yeovil Stand out on Social Media 6 October 2015Yeovil Stand out on Social Media 6 October 2015
Yeovil Stand out on Social Media 6 October 2015
 
The Performance Content Framework
The Performance Content FrameworkThe Performance Content Framework
The Performance Content Framework
 
Print for Profit - Digital for Growth
Print for Profit - Digital for GrowthPrint for Profit - Digital for Growth
Print for Profit - Digital for Growth
 
ATAK Interactive Marketing Success Stories
ATAK Interactive Marketing Success StoriesATAK Interactive Marketing Success Stories
ATAK Interactive Marketing Success Stories
 

Recently uploaded

dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)jennyeacort
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfBoston Institute of Analytics
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degreeyuu sss
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSINGmarianagonzalez07
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfSocial Samosa
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 

Recently uploaded (20)

Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
Call Us ➥97111√47426🤳Call Girls in Aerocity (Delhi NCR)
 
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdfPredicting Salary Using Data Science: A Comprehensive Analysis.pdf
Predicting Salary Using Data Science: A Comprehensive Analysis.pdf
 
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdfKantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
Kantar AI Summit- Under Embargo till Wednesday, 24th April 2024, 4 PM, IST.pdf
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
Call Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort ServiceCall Girls in Saket 99530🔝 56974 Escort Service
Call Girls in Saket 99530🔝 56974 Escort Service
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 

Real time ads personalization @ Spotify

  • 1. May 6th, 2014 Real-Time Personalization with Ad Tech @Spotify Kinshuk Mishra kinshuk@spotify.com @_kinshukmishra 1
  • 2. About Me • @Spotify since 2011 • Data and Backend engineering • With the Monetization team
  • 3. May 12, 2014 Spotify in numbers Started in 2006, available in 56 markets 20+ million songs, 20,000 added daily 24+ million active users, 6+ million subscribers 1.5 billion playlists
  • 4. May 12, 2014 Monetization at Spotify • $1 billion paid to rights holders since launch • 1 in every 4 Spotify users is a paying subscriber • Ad revenue pays for free tier music streaming • Build platform to power artist and music label promotions
  • 5. What is our mission? • Power the free tier with ads customers love. – Delight users, brands and artists with standout promotional experiences. – Deliver the right message for every moment. 5
  • 6. Delight users, brands and artists with standout promotional experience 6 • Ad formats need to be - Native - Actionable - Scalable - Engaging
  • 11. 11 !(Right message for every moment)
  • 12. Things we had to do • Make ads context aware. • Create measurable ad formats. • Build tools to help brands understand their audience. • Build flexible targeting infrastructure. • Analyze user behavior to improve ad relevancy. 12
  • 13. Why is real time interesting? • True assessment of the context - current view, last track, etc. • Immediate feedback - ad clicked, followed a playlist, etc. • Increased ad opportunities - hyperlocal, current mood, etc. 13 source : http://nativemobile.com/tag/real-time-bidding
  • 14. How to serve right message for every moment ? • Fix the WTFs for ads in the music context - Realtime short window activity analysis • Improve ad relevancy based on user behavior - (Realtime + Batch) long window activity analysis 14
  • 15. Some quick wins • Fix the WTFs for ads in the music context - Fix the “Not Safe For Kids” ads problem. - Fix the relevancy of ads in your music session. • Improve ad relevancy based on user behavior - Fix ad relevancy based on user’s musical taste. 15
  • 18. Our requirements • Scalable log collection • Capability to process logs in batch and realtime mode and aggregate user activity • Capability to store user profiles and enable serve time lookups • Ability to update and add new features to existing user profiles
  • 19. Bigdata @Spotify and choices • 700 node hadoop cluster • 400 GB service logs daily • 4.5 TB user data daily • 7500 hadoop jobs daily • 64 TB data generated daily • YARN Map-Reduce, Giraph, Storm, Spark, etc. ! 19
  • 20. Overall design and tech choices 20
  • 21. Source : http://tfosuccess.com/day-106-107-the-storm-arrived/ What is Storm? • Real time stream processing • Like Hadoop without HDFS • Like Map/Reduce with many reducer steps • Fault tolerant and guaranteed message processing 21
  • 22. Storm @Spotify • storm-0.8.0 • 22 node cluster • 15+ topologies • 200k tuples/second • ads, recommendation, analytics, monitoring, etc. 22 source: http://storm.incubator.apache.org/
  • 23. Use-case Use real-time session genre information to control ad serving in real-time 23
  • 24. Realtime activity analysis • Kafka -> Storm -> Memcached -> Targeting Backend • Soft realtime • Easy to scale 24
  • 26. Getting data across the globe 26
  • 28. May 12, 2014 Measuring effectiveness • Build ad quality scores from lower-level metrics • Positive response, avoidance, etc. • A/B test hypotheses, evaluate against quality scores • Build quality score optimization into real-time system
  • 29. May 6th, 2014 Want to join the band? https://www.spotify.com/us/jobs/ or https://twitter.com/Spotifyjobs ! Kinshuk Mishra kinshuk@spotify.com @_kinshukmishra