SlideShare uma empresa Scribd logo
1 de 18
Baixar para ler offline
Spotify’s Music
Recommendations
Lambda Architecture
Esh Kumar @eshvk
Emily Samuels @emilymsa
Overview
‣ Why Lambda?
‣ Use Case: Discover Recommendations
• Batch Architecture
• Real-time Architecture
• Challenges
‣ Future Work
Why Lambda?
• 1 new user every 3 seconds.
• Contextual, time based recs
more & more important
Discover
Recs
The Discover Page
Algorithmically generated fresh
recs for users.
The Discover Batch Pipeline
Machine Learning Deep Dive
Word2Vec
Words with similar
contexts have similar
meaning
Word2Vec
King – Man + Woman = Queen
Annoy
• Approximate
Nearest Neighbors
Oh Yeah!
• https://github.com/s
potify/annoy
Batch Architecture
Strengths
Intro to
Storm
Storm
• Distributed real-time
computation system
Storm @
Spotify
Real-time Architecture
• Workers die -> Cascading JVM
Process death
• Memcache flakiness
• Cassandra JVM problems due to
write/overwrite pattern
Challenges
Future/Ongoing Work
• Simplify the topology
• Keep listens for 24 hours
• Ongoing work on other
real time personalization
features.
Questions
Esh Kumar eshvk@spotify.com
Emily Samuels esamuels@spotify.com

Mais conteúdo relacionado

Mais procurados

Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...
Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...
Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...confluent
 
Kafka High Availability in multi data center setup with floating Observers wi...
Kafka High Availability in multi data center setup with floating Observers wi...Kafka High Availability in multi data center setup with floating Observers wi...
Kafka High Availability in multi data center setup with floating Observers wi...HostedbyConfluent
 
DeathNote of Microsoft Windows Kernel
DeathNote of Microsoft Windows KernelDeathNote of Microsoft Windows Kernel
DeathNote of Microsoft Windows KernelPeter Hlavaty
 
All about Zookeeper and ClickHouse Keeper.pdf
All about Zookeeper and ClickHouse Keeper.pdfAll about Zookeeper and ClickHouse Keeper.pdf
All about Zookeeper and ClickHouse Keeper.pdfAltinity Ltd
 
[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기NAVER D2
 
Building Instruqt, a scalable learning platform
Building Instruqt, a scalable learning platformBuilding Instruqt, a scalable learning platform
Building Instruqt, a scalable learning platformInstruqt
 
Apache Flink in the Cloud-Native Era
Apache Flink in the Cloud-Native EraApache Flink in the Cloud-Native Era
Apache Flink in the Cloud-Native EraFlink Forward
 
Battle of the Stream Processing Titans – Flink versus RisingWave
Battle of the Stream Processing Titans – Flink versus RisingWaveBattle of the Stream Processing Titans – Flink versus RisingWave
Battle of the Stream Processing Titans – Flink versus RisingWaveYingjun Wu
 
Building a fully managed stream processing platform on Flink at scale for Lin...
Building a fully managed stream processing platform on Flink at scale for Lin...Building a fully managed stream processing platform on Flink at scale for Lin...
Building a fully managed stream processing platform on Flink at scale for Lin...Flink Forward
 
Consumer offset management in Kafka
Consumer offset management in KafkaConsumer offset management in Kafka
Consumer offset management in KafkaJoel Koshy
 
Using the New Apache Flink Kubernetes Operator in a Production Deployment
Using the New Apache Flink Kubernetes Operator in a Production DeploymentUsing the New Apache Flink Kubernetes Operator in a Production Deployment
Using the New Apache Flink Kubernetes Operator in a Production DeploymentFlink Forward
 
Building large scale transactional data lake using apache hudi
Building large scale transactional data lake using apache hudiBuilding large scale transactional data lake using apache hudi
Building large scale transactional data lake using apache hudiBill Liu
 
Autoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive ModeAutoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive ModeFlink Forward
 
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...Altinity Ltd
 
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...Flink Forward
 
Apache Flink and what it is used for
Apache Flink and what it is used forApache Flink and what it is used for
Apache Flink and what it is used forAljoscha Krettek
 
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...HostedbyConfluent
 
Flink Forward SF 2017: Timo Walther - Table & SQL API – unified APIs for bat...
Flink Forward SF 2017: Timo Walther -  Table & SQL API – unified APIs for bat...Flink Forward SF 2017: Timo Walther -  Table & SQL API – unified APIs for bat...
Flink Forward SF 2017: Timo Walther - Table & SQL API – unified APIs for bat...Flink Forward
 

Mais procurados (20)

Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...
Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...
Disaster Recovery with MirrorMaker 2.0 (Ryanne Dolan, Cloudera) Kafka Summit ...
 
Kafka High Availability in multi data center setup with floating Observers wi...
Kafka High Availability in multi data center setup with floating Observers wi...Kafka High Availability in multi data center setup with floating Observers wi...
Kafka High Availability in multi data center setup with floating Observers wi...
 
DeathNote of Microsoft Windows Kernel
DeathNote of Microsoft Windows KernelDeathNote of Microsoft Windows Kernel
DeathNote of Microsoft Windows Kernel
 
All about Zookeeper and ClickHouse Keeper.pdf
All about Zookeeper and ClickHouse Keeper.pdfAll about Zookeeper and ClickHouse Keeper.pdf
All about Zookeeper and ClickHouse Keeper.pdf
 
[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기[234]멀티테넌트 하둡 클러스터 운영 경험기
[234]멀티테넌트 하둡 클러스터 운영 경험기
 
Building Instruqt, a scalable learning platform
Building Instruqt, a scalable learning platformBuilding Instruqt, a scalable learning platform
Building Instruqt, a scalable learning platform
 
Apache Flink in the Cloud-Native Era
Apache Flink in the Cloud-Native EraApache Flink in the Cloud-Native Era
Apache Flink in the Cloud-Native Era
 
Battle of the Stream Processing Titans – Flink versus RisingWave
Battle of the Stream Processing Titans – Flink versus RisingWaveBattle of the Stream Processing Titans – Flink versus RisingWave
Battle of the Stream Processing Titans – Flink versus RisingWave
 
Building a fully managed stream processing platform on Flink at scale for Lin...
Building a fully managed stream processing platform on Flink at scale for Lin...Building a fully managed stream processing platform on Flink at scale for Lin...
Building a fully managed stream processing platform on Flink at scale for Lin...
 
Consumer offset management in Kafka
Consumer offset management in KafkaConsumer offset management in Kafka
Consumer offset management in Kafka
 
Using the New Apache Flink Kubernetes Operator in a Production Deployment
Using the New Apache Flink Kubernetes Operator in a Production DeploymentUsing the New Apache Flink Kubernetes Operator in a Production Deployment
Using the New Apache Flink Kubernetes Operator in a Production Deployment
 
Building large scale transactional data lake using apache hudi
Building large scale transactional data lake using apache hudiBuilding large scale transactional data lake using apache hudi
Building large scale transactional data lake using apache hudi
 
Autoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive ModeAutoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive Mode
 
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
 
The Stream Processor as a Database Apache Flink
The Stream Processor as a Database Apache FlinkThe Stream Processor as a Database Apache Flink
The Stream Processor as a Database Apache Flink
 
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...
Dynamically Scaling Data Streams across Multiple Kafka Clusters with Zero Fli...
 
Apache Flink and what it is used for
Apache Flink and what it is used forApache Flink and what it is used for
Apache Flink and what it is used for
 
Hive tuning
Hive tuningHive tuning
Hive tuning
 
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...
Improving fault tolerance and scaling out in Kafka Streams with Bill Bejeck |...
 
Flink Forward SF 2017: Timo Walther - Table & SQL API – unified APIs for bat...
Flink Forward SF 2017: Timo Walther -  Table & SQL API – unified APIs for bat...Flink Forward SF 2017: Timo Walther -  Table & SQL API – unified APIs for bat...
Flink Forward SF 2017: Timo Walther - Table & SQL API – unified APIs for bat...
 

Destaque

Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.
Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.
Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.Hubbub Media
 
A thousand fronts: on the architectures I like
A thousand fronts: on the architectures I likeA thousand fronts: on the architectures I like
A thousand fronts: on the architectures I likeDavide Tommaso Ferrando
 
4.4 mb portfolio print 2012-2016
4.4 mb portfolio print 2012-20164.4 mb portfolio print 2012-2016
4.4 mb portfolio print 2012-2016Meghan Garnett
 
We’ve created a monster! Truth and fiction in SOA
We’ve created a monster! Truth and fiction in SOAWe’ve created a monster! Truth and fiction in SOA
We’ve created a monster! Truth and fiction in SOAJon Collins
 
Moving into movies - using video in E-Learning
Moving into movies - using video in E-Learning Moving into movies - using video in E-Learning
Moving into movies - using video in E-Learning Aurion Learning
 
Architectural structures world Wide
Architectural structures   world WideArchitectural structures   world Wide
Architectural structures world WideSagun Rakibe
 
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)360i
 
exploring architecture and music
exploring architecture and musicexploring architecture and music
exploring architecture and musicmichielmoyaert
 
Big Idea: FIction & Non-Fiction
Big Idea: FIction & Non-FictionBig Idea: FIction & Non-Fiction
Big Idea: FIction & Non-FictionAngela Maiers
 
WA1. Cycle Fullcourseware, September 2008
WA1. Cycle Fullcourseware, September 2008WA1. Cycle Fullcourseware, September 2008
WA1. Cycle Fullcourseware, September 2008tanglay
 
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015PeopleBrowsr
 
Architecture Music Acoustics, Part 2
Architecture Music Acoustics, Part 2Architecture Music Acoustics, Part 2
Architecture Music Acoustics, Part 2Shannon Mattern
 
The Evolution of Hadoop at Spotify - Through Failures and Pain
The Evolution of Hadoop at Spotify - Through Failures and PainThe Evolution of Hadoop at Spotify - Through Failures and Pain
The Evolution of Hadoop at Spotify - Through Failures and PainRafał Wojdyła
 
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...Davide Tommaso Ferrando
 
Subjects in realistic fiction revised
Subjects in realistic fiction revisedSubjects in realistic fiction revised
Subjects in realistic fiction revisedKrishna Ponce
 

Destaque (20)

Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.
Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.
Story, Sci-Fi & Transmedia to develop Corporate Technology Strategies.
 
A thousand fronts: on the architectures I like
A thousand fronts: on the architectures I likeA thousand fronts: on the architectures I like
A thousand fronts: on the architectures I like
 
4.4 mb portfolio print 2012-2016
4.4 mb portfolio print 2012-20164.4 mb portfolio print 2012-2016
4.4 mb portfolio print 2012-2016
 
Math music and architecture
Math music and architectureMath music and architecture
Math music and architecture
 
We’ve created a monster! Truth and fiction in SOA
We’ve created a monster! Truth and fiction in SOAWe’ve created a monster! Truth and fiction in SOA
We’ve created a monster! Truth and fiction in SOA
 
Moving into movies - using video in E-Learning
Moving into movies - using video in E-Learning Moving into movies - using video in E-Learning
Moving into movies - using video in E-Learning
 
Barnes and Noble
Barnes and NobleBarnes and Noble
Barnes and Noble
 
Architectural structures world Wide
Architectural structures   world WideArchitectural structures   world Wide
Architectural structures world Wide
 
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)
360i Idea Safari: The Hunt of the Mysterious BIG IDEA (Presented at Cannes 2012)
 
exploring architecture and music
exploring architecture and musicexploring architecture and music
exploring architecture and music
 
Postmodernism
PostmodernismPostmodernism
Postmodernism
 
Big Idea: FIction & Non-Fiction
Big Idea: FIction & Non-FictionBig Idea: FIction & Non-Fiction
Big Idea: FIction & Non-Fiction
 
WA1. Cycle Fullcourseware, September 2008
WA1. Cycle Fullcourseware, September 2008WA1. Cycle Fullcourseware, September 2008
WA1. Cycle Fullcourseware, September 2008
 
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015
PeopleBrowsr Presents A Brief Cartoon History of Social Networking 1930-2015
 
The Spencer Pavillion 100152598
The Spencer Pavillion 100152598The Spencer Pavillion 100152598
The Spencer Pavillion 100152598
 
Architecture Music Acoustics, Part 2
Architecture Music Acoustics, Part 2Architecture Music Acoustics, Part 2
Architecture Music Acoustics, Part 2
 
The Evolution of Hadoop at Spotify - Through Failures and Pain
The Evolution of Hadoop at Spotify - Through Failures and PainThe Evolution of Hadoop at Spotify - Through Failures and Pain
The Evolution of Hadoop at Spotify - Through Failures and Pain
 
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...
But Today We Collect Bullshit: Architecture and Storytelling in the Age of So...
 
Urban Design
Urban DesignUrban Design
Urban Design
 
Subjects in realistic fiction revised
Subjects in realistic fiction revisedSubjects in realistic fiction revised
Subjects in realistic fiction revised
 

Semelhante a Spotify's Lambda Architecture for Music Recommendations

Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017
Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017
Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017Amazon Web Services
 
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02Derek Ashmore
 
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)Spark Summit
 
Aws Lambda for Java Architects - Illinois VJug -2016-05-03
Aws Lambda for Java Architects - Illinois VJug -2016-05-03Aws Lambda for Java Architects - Illinois VJug -2016-05-03
Aws Lambda for Java Architects - Illinois VJug -2016-05-03Derek Ashmore
 
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, Europe
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, EuropePatterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, Europe
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, EuropeFlip Kromer
 
Serverless Architecture Patterns
Serverless Architecture PatternsServerless Architecture Patterns
Serverless Architecture PatternsAmazon Web Services
 
Wait! What’s going on inside my database? (PASS 2023 Update)
Wait! What’s going on inside my database? (PASS 2023 Update)Wait! What’s going on inside my database? (PASS 2023 Update)
Wait! What’s going on inside my database? (PASS 2023 Update)Jeremy Schneider
 
Streaming with Spring Cloud Stream and Apache Kafka - Soby Chacko
Streaming with Spring Cloud Stream and Apache Kafka - Soby ChackoStreaming with Spring Cloud Stream and Apache Kafka - Soby Chacko
Streaming with Spring Cloud Stream and Apache Kafka - Soby ChackoVMware Tanzu
 
Serverless Architectural Patterns and Best Practices
Serverless Architectural Patterns and Best PracticesServerless Architectural Patterns and Best Practices
Serverless Architectural Patterns and Best PracticesAmazon Web Services
 
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Example
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life ExampleKafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Example
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Exampleconfluent
 
Samza at LinkedIn: Taking Stream Processing to the Next Level
Samza at LinkedIn: Taking Stream Processing to the Next LevelSamza at LinkedIn: Taking Stream Processing to the Next Level
Samza at LinkedIn: Taking Stream Processing to the Next LevelMartin Kleppmann
 
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOT
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOTAWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOT
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOTAmazon Web Services
 
From a kafkaesque story to The Promised Land
From a kafkaesque story to The Promised LandFrom a kafkaesque story to The Promised Land
From a kafkaesque story to The Promised LandRan Silberman
 
Exactly-once Semantics in Apache Kafka
Exactly-once Semantics in Apache KafkaExactly-once Semantics in Apache Kafka
Exactly-once Semantics in Apache Kafkaconfluent
 
Serverless conference-labrador-at-2018
Serverless conference-labrador-at-2018Serverless conference-labrador-at-2018
Serverless conference-labrador-at-2018Antonio Terreno
 
Serverless Architectural Patterns and Best Practices | AWS
Serverless Architectural Patterns and Best Practices | AWSServerless Architectural Patterns and Best Practices | AWS
Serverless Architectural Patterns and Best Practices | AWSAWS Germany
 
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019Derek Ashmore
 
Apache Kafka - Scalable Message-Processing and more !
Apache Kafka - Scalable Message-Processing and more !Apache Kafka - Scalable Message-Processing and more !
Apache Kafka - Scalable Message-Processing and more !Guido Schmutz
 

Semelhante a Spotify's Lambda Architecture for Music Recommendations (20)

Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017
Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017
Real Time Data Processing Using AWS Lambda - DevDay Los Angeles 2017
 
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02
Aws Lambda for Java Architects - Illinois JUG-Northwest -2016-08-02
 
Akka streams kafka kinesis
Akka streams kafka kinesisAkka streams kafka kinesis
Akka streams kafka kinesis
 
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)
Spark and Spark Streaming at Netfix-(Kedar Sedekar and Monal Daxini, Netflix)
 
Aws Lambda for Java Architects - Illinois VJug -2016-05-03
Aws Lambda for Java Architects - Illinois VJug -2016-05-03Aws Lambda for Java Architects - Illinois VJug -2016-05-03
Aws Lambda for Java Architects - Illinois VJug -2016-05-03
 
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, Europe
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, EuropePatterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, Europe
Patterns of the Lambda Architecture -- 2015 April -- Hadoop Summit, Europe
 
Serverless Architecture Patterns
Serverless Architecture PatternsServerless Architecture Patterns
Serverless Architecture Patterns
 
Dystopia as a Service
Dystopia as a ServiceDystopia as a Service
Dystopia as a Service
 
Wait! What’s going on inside my database? (PASS 2023 Update)
Wait! What’s going on inside my database? (PASS 2023 Update)Wait! What’s going on inside my database? (PASS 2023 Update)
Wait! What’s going on inside my database? (PASS 2023 Update)
 
Streaming with Spring Cloud Stream and Apache Kafka - Soby Chacko
Streaming with Spring Cloud Stream and Apache Kafka - Soby ChackoStreaming with Spring Cloud Stream and Apache Kafka - Soby Chacko
Streaming with Spring Cloud Stream and Apache Kafka - Soby Chacko
 
Serverless Architectural Patterns and Best Practices
Serverless Architectural Patterns and Best PracticesServerless Architectural Patterns and Best Practices
Serverless Architectural Patterns and Best Practices
 
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Example
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life ExampleKafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Example
Kafka Summit NYC 2017 Introduction to Kafka Streams with a Real-life Example
 
Samza at LinkedIn: Taking Stream Processing to the Next Level
Samza at LinkedIn: Taking Stream Processing to the Next LevelSamza at LinkedIn: Taking Stream Processing to the Next Level
Samza at LinkedIn: Taking Stream Processing to the Next Level
 
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOT
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOTAWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOT
AWS APAC Webinar Week - Big Data on AWS. RedShift, EMR, & IOT
 
From a kafkaesque story to The Promised Land
From a kafkaesque story to The Promised LandFrom a kafkaesque story to The Promised Land
From a kafkaesque story to The Promised Land
 
Exactly-once Semantics in Apache Kafka
Exactly-once Semantics in Apache KafkaExactly-once Semantics in Apache Kafka
Exactly-once Semantics in Apache Kafka
 
Serverless conference-labrador-at-2018
Serverless conference-labrador-at-2018Serverless conference-labrador-at-2018
Serverless conference-labrador-at-2018
 
Serverless Architectural Patterns and Best Practices | AWS
Serverless Architectural Patterns and Best Practices | AWSServerless Architectural Patterns and Best Practices | AWS
Serverless Architectural Patterns and Best Practices | AWS
 
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019
AWS Lambda: Best Practices and Common Mistakes - Dev Ops West 2019
 
Apache Kafka - Scalable Message-Processing and more !
Apache Kafka - Scalable Message-Processing and more !Apache Kafka - Scalable Message-Processing and more !
Apache Kafka - Scalable Message-Processing and more !
 

Último

What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesVictoriaMetrics
 
2024 DevNexus Patterns for Resiliency: Shuffle shards
2024 DevNexus Patterns for Resiliency: Shuffle shards2024 DevNexus Patterns for Resiliency: Shuffle shards
2024 DevNexus Patterns for Resiliency: Shuffle shardsChristopher Curtin
 
Zer0con 2024 final share short version.pdf
Zer0con 2024 final share short version.pdfZer0con 2024 final share short version.pdf
Zer0con 2024 final share short version.pdfmaor17
 
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...OnePlan Solutions
 
Ronisha Informatics Private Limited Catalogue
Ronisha Informatics Private Limited CatalogueRonisha Informatics Private Limited Catalogue
Ronisha Informatics Private Limited Catalogueitservices996
 
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...OnePlan Solutions
 
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdfAndrey Devyatkin
 
Strategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsStrategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsJean Silva
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonApplitools
 
Large Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and RepairLarge Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and RepairLionel Briand
 
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...kalichargn70th171
 
SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?Alexandre Beguel
 
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxThe Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxRTS corp
 
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdf
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdfEnhancing Supply Chain Visibility with Cargo Cloud Solutions.pdf
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdfRTS corp
 
Advantages of Cargo Cloud Solutions.pptx
Advantages of Cargo Cloud Solutions.pptxAdvantages of Cargo Cloud Solutions.pptx
Advantages of Cargo Cloud Solutions.pptxRTS corp
 
Understanding Flamingo - DeepMind's VLM Architecture
Understanding Flamingo - DeepMind's VLM ArchitectureUnderstanding Flamingo - DeepMind's VLM Architecture
Understanding Flamingo - DeepMind's VLM Architecturerahul_net
 
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesAmazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesKrzysztofKkol1
 
eSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolseSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolsosttopstonverter
 
Best Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITBest Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITmanoharjgpsolutions
 
Effectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorEffectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorTier1 app
 

Último (20)

What’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 UpdatesWhat’s New in VictoriaMetrics: Q1 2024 Updates
What’s New in VictoriaMetrics: Q1 2024 Updates
 
2024 DevNexus Patterns for Resiliency: Shuffle shards
2024 DevNexus Patterns for Resiliency: Shuffle shards2024 DevNexus Patterns for Resiliency: Shuffle shards
2024 DevNexus Patterns for Resiliency: Shuffle shards
 
Zer0con 2024 final share short version.pdf
Zer0con 2024 final share short version.pdfZer0con 2024 final share short version.pdf
Zer0con 2024 final share short version.pdf
 
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
Tech Tuesday Slides - Introduction to Project Management with OnePlan's Work ...
 
Ronisha Informatics Private Limited Catalogue
Ronisha Informatics Private Limited CatalogueRonisha Informatics Private Limited Catalogue
Ronisha Informatics Private Limited Catalogue
 
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
Revolutionizing the Digital Transformation Office - Leveraging OnePlan’s AI a...
 
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf
2024-04-09 - From Complexity to Clarity - AWS Summit AMS.pdf
 
Strategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero resultsStrategies for using alternative queries to mitigate zero results
Strategies for using alternative queries to mitigate zero results
 
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + KobitonLeveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
Leveraging AI for Mobile App Testing on Real Devices | Applitools + Kobiton
 
Large Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and RepairLarge Language Models for Test Case Evolution and Repair
Large Language Models for Test Case Evolution and Repair
 
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...
The Ultimate Guide to Performance Testing in Low-Code, No-Code Environments (...
 
SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?SAM Training Session - How to use EXCEL ?
SAM Training Session - How to use EXCEL ?
 
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptxThe Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
The Role of IoT and Sensor Technology in Cargo Cloud Solutions.pptx
 
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdf
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdfEnhancing Supply Chain Visibility with Cargo Cloud Solutions.pdf
Enhancing Supply Chain Visibility with Cargo Cloud Solutions.pdf
 
Advantages of Cargo Cloud Solutions.pptx
Advantages of Cargo Cloud Solutions.pptxAdvantages of Cargo Cloud Solutions.pptx
Advantages of Cargo Cloud Solutions.pptx
 
Understanding Flamingo - DeepMind's VLM Architecture
Understanding Flamingo - DeepMind's VLM ArchitectureUnderstanding Flamingo - DeepMind's VLM Architecture
Understanding Flamingo - DeepMind's VLM Architecture
 
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilitiesAmazon Bedrock in Action - presentation of the Bedrock's capabilities
Amazon Bedrock in Action - presentation of the Bedrock's capabilities
 
eSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration toolseSoftTools IMAP Backup Software and migration tools
eSoftTools IMAP Backup Software and migration tools
 
Best Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh ITBest Angular 17 Classroom & Online training - Naresh IT
Best Angular 17 Classroom & Online training - Naresh IT
 
Effectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryErrorEffectively Troubleshoot 9 Types of OutOfMemoryError
Effectively Troubleshoot 9 Types of OutOfMemoryError
 

Spotify's Lambda Architecture for Music Recommendations

Notas do Editor

  1. Emily Introduce Emily and Esh give background on what we do and who we are Discover Page Google Now Playlist Recommendations Discover Weekly Personalization features
  2. Emily
  3. Emily Scalding
  4. Esh
  5. Emily Scalding
  6. Emily Scalding
  7. Esh Talk about high intent vs low intent when talking about building user vectors.
  8. Esh A single machine = 100 billion words a day. Word2vec works on the basis of the distributional hypothesis. The idea being that words which appear in the same context, have similar meanings. One model in the word2vec framework that we use is the Skipgram model. So essentially, what happens is that we go through documents, for each word in the document, we try to predict what the future or previous words should be. Mathematically there is a way to show that this is like factorizing a word-context matrix. For us, playlists are documents, and words are songs that we would like to learn vectors for. The advantage of something like word2vec is that at the end, you have a geometry defined on top of vectors. So you could add the tracks of an artists to get the vector representation of an artist.
  9. Esh Static indices that can be shipped around. Core principle being LSH.
  10. Esh reflective of their whole music taste
  11. Emily We are the first team to build a production ready personalization feature using Storm at Spotify. The Kafka queues were optimized for Hadoop ingestion Localized close to the Hadoop Cluster in London.
  12. Emily Spouts, bolts, tuples Topology to stitch together the bolts
  13. Emily First team at Spotify to do real-time recommendations The Kafka queues were optimized for Hadoop ingestion. The Kafka cluster was localized close to the Hadoop cluster. Both in our data center in London. Localized close to the Hadoop Cluster in London.
  14. Emily Write into LON Cassandra cluster Use sparkey files to store vector info Splash to ship sparkey files not writing user vectors, only writing out the recs
  15. Esh Despite the challenges, we had a successful ab test and are running this in production
  16. Emily Write out the vectors, not just the recs Service for vectors Aggregation service on top of vectors to compute recs Use real-time data to improve recs for all users
  17. Emily Why Lambda The Batch Architecture Real-time Architecture Challenges Future Work