SlideShare une entreprise Scribd logo
1  sur  15
Real-Time Recommender Systems
Bay Area Search Meetup at eBay
April 25, 2012




                          Balu Rajagopal
Goal of Recommenders                                                     INSTANT INTELLIGENCE




      1. Increase number of items sold

      2. Cross-Sell, Up-Sell diverse items

      3. Increase Customer Satisfaction

      4. Build Loyalty

      5. Improve User Experience



Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                     2
Recommendations                                                          INSTANT INTELLIGENCE




         USERS




           Search                                 Recommendations



                                                      Products
                                                      Web sites
                                                      Social networks
                               ITEMS
                                                      Blogs
                                                      News
                                                      ….



Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                     3
Two Challenges                                                           INSTANT INTELLIGENCE




   Make a Personalized Recommendation
           –    Multi-Dimensional Data
           –    Streams: Social, Activity, Apps, Tweets, Actions, …
           –    Demographic
           –    Temporal, Spatial
   Do it in real-time
           – Query to Analysis to Visualization
           – User Experience (UX)
           – System Constraints – Network, Capacity, SLA

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                     4
Problem Space                                                                              INSTANT INTELLIGENCE



                                                            Cetas Instant Intelligence Framework




                                                                                                                      Secs or Less
                   Large




                                                                                                                                     RESPONSE TIME TO USER
DATA DIMENSIONS




                                                                                                                      Minutes
                  Medium




                                                                                                                      Hours
                   Small




                                      Gigabytes                                      Terabytes     Petabytes

                                                                           ANALYSIS VOLUME
                  Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                                  5
Real-time Recommender System                                                              INSTANT INTELLIGENCE




        Inputs                                     Terabytes of Multi-Dimensional data




  Preprocessing                                    Reduction

                                                                                     @ Scale
                                                                                     @ Speed
       Analysis                                    Classifying, Clustering




       Output                                      Prediction, Recommendation

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                    6
Real-time Recommender System                                                                 INSTANT INTELLIGENCE


                                              • Spatial
        Inputs                                • Temporal
                                                                           • Demographic
                                              • Personal                   • Psychographic
                                                                           • Behavioral


  Preprocessing                                    Reduction




       Analysis                                    Classifying, Clustering




       Output                                      Predictions, Recommendations, Patterns

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                       7
Real-time Recommender System                                                                     INSTANT INTELLIGENCE


                                              • Spatial
        Inputs                                • Temporal
                                                                           • Demographic
                                              • Personal                   • Psychographic
                                                                           • Behavioral
                                              • Distance Measures
  Preprocessing                               • Sampling
                                                                                         • PCA
                                              • Dimensionality Reduction
                                                                                         • SVD



       Analysis                                    Classifying, Clustering




       Output                                      Predictions, Recommendations, Patterns

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                           8
Real-time Recommender System                                                                      INSTANT INTELLIGENCE


                                              • Spatial
        Inputs                                • Temporal
                                                                           • Demographic
                                              • Personal                   • Psychographic
                                                                           • Behavioral
                                              • Distance Measures
  Preprocessing                               • Sampling
                                                                                         • PCA
                                              • Dimensionality Reduction
                                                                                         • SVD

                                              • Predictors                     • Classification
       Analysis
                                              • Descriptors                    • Association
                                                                               • Clustering

       Output

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                            9
Real-time Recommender System                                                                      INSTANT INTELLIGENCE


                                              • Spatial
        Inputs                                • Temporal
                                                                           • Demographic
                                              • Personal                   • Psychographic
                                                                           • Behavioral
                                              • Distance Measures
  Preprocessing                               • Sampling
                                                                                         • PCA
                                              • Dimensionality Reduction
                                                                                         • SVD

                                              • Predictors                     • Classification
       Analysis
                                              • Descriptors                    • Association
                                                                               • Clustering
                                              • Predictions
       Output                                 • Recommendations
                                              • Patterns
Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                           10
Big Data Analytics – eCommerce
                                                                                        INSTANT INTELLIGENCE


   Input data                                                    Clustering   Closed-loop Action



         User
    transactions
     live stream                                                                Product placement
                                                                                     decision



   Demographics
    data stream

                                                                                  Category, sub-
                                                                                 category sorting

    Online app
   events stream




                                                                                  New product
   Ad placement                                                                     offering
      stream




   Other streams
         …                                                                       Other actions …

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                 11
Real-time Stream Processing                                                                   INSTANT INTELLIGENCE




                 Billions of Events
                                                      I
                                                      n
                                                      d
                                                      e
                                                      x               CEP




                          RAM
                         Cache                                                     Joins
                       RAM Disk                                                    Aggregates

                                                      HBase
                                                                            HDFS

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                                         12
Wrap-up                                                                  INSTANT INTELLIGENCE




   Personalized Recommendation Engine
           – Non-trivial
           – Focus on Specific Use Case
   Real-time
           – Distributed Indexing
           – Pre-computation
           – Compact store (in memory, on disk)
           – Parallelization

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                    13
References                                                               INSTANT INTELLIGENCE




   Mining Massive Datasets
           – Free eBook – Anand Rajaraman, Jeff Ullman
           – cs246.stanford.edu
   Introduction to Data Mining
           – Tan, Steinback, Kumar
   Introduction to Recommender Systems
    Handbook
           – Ricci, Rokach, Shapira

Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                    14
INSTANT INTELLIGENCE




Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE                    15

Contenu connexe

Tendances

02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx
02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx
02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptxTraitet Thepbandansuk
 
Overview crowd funding
Overview crowd fundingOverview crowd funding
Overview crowd fundingLen Chermack
 
Session 803 dan lafever fusion11 final copy
Session 803 dan lafever fusion11 final copySession 803 dan lafever fusion11 final copy
Session 803 dan lafever fusion11 final copyDaniel C. Lafever
 
Automated Management of Intelligent Devices
Automated Management of Intelligent DevicesAutomated Management of Intelligent Devices
Automated Management of Intelligent Devicesuplogix
 
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...What our Partners and Customers are saying about Webroot SecureAnywhere Busin...
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...Webroot
 
It performance suite_overview_ebc_11062012
It performance suite_overview_ebc_11062012It performance suite_overview_ebc_11062012
It performance suite_overview_ebc_11062012Lilian Schaffer
 
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead Data
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead DataM12S23 - Right-sizing Your Information Footprint by Chucking Your Dead Data
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead DataMER Conference
 
Morgenmøde business intelligence targit
Morgenmøde  business intelligence targitMorgenmøde  business intelligence targit
Morgenmøde business intelligence targitIsaLindbaek
 

Tendances (9)

02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx
02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx
02 design new_it_service_dept_apendix_industrialexpertise_feb12.pptx
 
Overview crowd funding
Overview crowd fundingOverview crowd funding
Overview crowd funding
 
Session 803 dan lafever fusion11 final copy
Session 803 dan lafever fusion11 final copySession 803 dan lafever fusion11 final copy
Session 803 dan lafever fusion11 final copy
 
Automated Management of Intelligent Devices
Automated Management of Intelligent DevicesAutomated Management of Intelligent Devices
Automated Management of Intelligent Devices
 
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...What our Partners and Customers are saying about Webroot SecureAnywhere Busin...
What our Partners and Customers are saying about Webroot SecureAnywhere Busin...
 
eTrax, Staff Monitoring System
eTrax, Staff Monitoring SystemeTrax, Staff Monitoring System
eTrax, Staff Monitoring System
 
It performance suite_overview_ebc_11062012
It performance suite_overview_ebc_11062012It performance suite_overview_ebc_11062012
It performance suite_overview_ebc_11062012
 
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead Data
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead DataM12S23 - Right-sizing Your Information Footprint by Chucking Your Dead Data
M12S23 - Right-sizing Your Information Footprint by Chucking Your Dead Data
 
Morgenmøde business intelligence targit
Morgenmøde  business intelligence targitMorgenmøde  business intelligence targit
Morgenmøde business intelligence targit
 

En vedette

Changes of sexual practices of people living with hiv after initiation of ant...
Changes of sexual practices of people living with hiv after initiation of ant...Changes of sexual practices of people living with hiv after initiation of ant...
Changes of sexual practices of people living with hiv after initiation of ant...PinHealth
 
Design of Nuclear Security Regime to Combat Nuclear Terrorism
Design of Nuclear Security Regime to Combat Nuclear TerrorismDesign of Nuclear Security Regime to Combat Nuclear Terrorism
Design of Nuclear Security Regime to Combat Nuclear TerrorismAM Publications
 
SAE INSTITUTE Film prospectus
SAE INSTITUTE Film prospectusSAE INSTITUTE Film prospectus
SAE INSTITUTE Film prospectusAbhishek Bajaj
 
Supermarkets x factor
Supermarkets x factorSupermarkets x factor
Supermarkets x factorQueen Dy
 
Cambridge international examinations
Cambridge international examinationsCambridge international examinations
Cambridge international examinationsGhulam Qadir .
 
CA 3.05 Copernican Revolution
CA 3.05 Copernican RevolutionCA 3.05 Copernican Revolution
CA 3.05 Copernican RevolutionStephen Kwong
 
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems -  ACM RecSys 2013 tutorialLearning to Rank for Recommender Systems -  ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorialAlexandros Karatzoglou
 
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Xavier Amatriain
 

En vedette (12)

Prathiba (1)
Prathiba (1)Prathiba (1)
Prathiba (1)
 
Changes of sexual practices of people living with hiv after initiation of ant...
Changes of sexual practices of people living with hiv after initiation of ant...Changes of sexual practices of people living with hiv after initiation of ant...
Changes of sexual practices of people living with hiv after initiation of ant...
 
My recent work
My recent workMy recent work
My recent work
 
Design of Nuclear Security Regime to Combat Nuclear Terrorism
Design of Nuclear Security Regime to Combat Nuclear TerrorismDesign of Nuclear Security Regime to Combat Nuclear Terrorism
Design of Nuclear Security Regime to Combat Nuclear Terrorism
 
SAE INSTITUTE Film prospectus
SAE INSTITUTE Film prospectusSAE INSTITUTE Film prospectus
SAE INSTITUTE Film prospectus
 
Supermarkets x factor
Supermarkets x factorSupermarkets x factor
Supermarkets x factor
 
Cambridge international examinations
Cambridge international examinationsCambridge international examinations
Cambridge international examinations
 
CA 3.05 Copernican Revolution
CA 3.05 Copernican RevolutionCA 3.05 Copernican Revolution
CA 3.05 Copernican Revolution
 
up dated cv
up dated cv up dated cv
up dated cv
 
ป๊อปอาย
ป๊อปอายป๊อปอาย
ป๊อปอาย
 
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems -  ACM RecSys 2013 tutorialLearning to Rank for Recommender Systems -  ACM RecSys 2013 tutorial
Learning to Rank for Recommender Systems - ACM RecSys 2013 tutorial
 
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)Recommender Systems (Machine Learning Summer School 2014 @ CMU)
Recommender Systems (Machine Learning Summer School 2014 @ CMU)
 

Similaire à Cetas Presentation on Real-time Recommendation Systems

SAS Big Data Forum - Transforming Big Data into Corporate Gold
SAS Big Data Forum - Transforming Big Data into Corporate GoldSAS Big Data Forum - Transforming Big Data into Corporate Gold
SAS Big Data Forum - Transforming Big Data into Corporate GoldLouis Fernandes
 
New Analytical Architectures for Big Data
New Analytical Architectures for Big DataNew Analytical Architectures for Big Data
New Analytical Architectures for Big DataCasey Kiernan
 
Prediktiv analys och kundlojalitet
Prediktiv analys och kundlojalitetPrediktiv analys och kundlojalitet
Prediktiv analys och kundlojalitetIBM Sverige
 
Big Data Needs Big Analytics
Big Data Needs Big AnalyticsBig Data Needs Big Analytics
Big Data Needs Big AnalyticsDeepak Ramanathan
 
Analyzing Multi-Structured Data
Analyzing Multi-Structured DataAnalyzing Multi-Structured Data
Analyzing Multi-Structured DataDataWorks Summit
 
Social media mining hicss 46 part 2
Social media mining   hicss 46 part 2Social media mining   hicss 46 part 2
Social media mining hicss 46 part 2Dave King
 
Mesh Labs Introduction June 2012
Mesh Labs Introduction June 2012Mesh Labs Introduction June 2012
Mesh Labs Introduction June 2012Umesh Ramalingachar
 
Scaling MySQL: Catch 22 of Read Write Splitting
Scaling MySQL: Catch 22 of Read Write SplittingScaling MySQL: Catch 22 of Read Write Splitting
Scaling MySQL: Catch 22 of Read Write SplittingScaleBase
 
Dataiku r users group v2
Dataiku   r users group v2Dataiku   r users group v2
Dataiku r users group v2Cdiscount
 
The Road to Business Agility
The Road to Business AgilityThe Road to Business Agility
The Road to Business AgilitySrini Koushik
 
Teradata Big Data London Seminar
Teradata Big Data London SeminarTeradata Big Data London Seminar
Teradata Big Data London SeminarHortonworks
 
Big Data: A Big Trap for Product Development
Big Data: A Big Trap for Product DevelopmentBig Data: A Big Trap for Product Development
Big Data: A Big Trap for Product DevelopmentStrategy 2 Market, Inc,
 
Module 3 Adapative Customer Experience Final
Module 3 Adapative Customer Experience FinalModule 3 Adapative Customer Experience Final
Module 3 Adapative Customer Experience FinalVivastream
 
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOut
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOutScaleBase Webinar 8.16: ScaleUp vs. ScaleOut
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOutScaleBase
 
Big data meets big analytics
Big data meets big analyticsBig data meets big analytics
Big data meets big analyticsDeepak Ramanathan
 
Process Steps
Process StepsProcess Steps
Process StepsmfeKEG
 
Information Management: Answering Today’s Enterprise Challenge
Information Management: Answering Today’s Enterprise ChallengeInformation Management: Answering Today’s Enterprise Challenge
Information Management: Answering Today’s Enterprise ChallengeBob Rhubart
 
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data European Data Forum
 

Similaire à Cetas Presentation on Real-time Recommendation Systems (20)

Computers Final Report.ppt
Computers Final Report.pptComputers Final Report.ppt
Computers Final Report.ppt
 
SAS Big Data Forum - Transforming Big Data into Corporate Gold
SAS Big Data Forum - Transforming Big Data into Corporate GoldSAS Big Data Forum - Transforming Big Data into Corporate Gold
SAS Big Data Forum - Transforming Big Data into Corporate Gold
 
New Analytical Architectures for Big Data
New Analytical Architectures for Big DataNew Analytical Architectures for Big Data
New Analytical Architectures for Big Data
 
Prediktiv analys och kundlojalitet
Prediktiv analys och kundlojalitetPrediktiv analys och kundlojalitet
Prediktiv analys och kundlojalitet
 
Big Data Needs Big Analytics
Big Data Needs Big AnalyticsBig Data Needs Big Analytics
Big Data Needs Big Analytics
 
Analyzing Multi-Structured Data
Analyzing Multi-Structured DataAnalyzing Multi-Structured Data
Analyzing Multi-Structured Data
 
Social media mining hicss 46 part 2
Social media mining   hicss 46 part 2Social media mining   hicss 46 part 2
Social media mining hicss 46 part 2
 
Mesh Labs Introduction June 2012
Mesh Labs Introduction June 2012Mesh Labs Introduction June 2012
Mesh Labs Introduction June 2012
 
Scaling MySQL: Catch 22 of Read Write Splitting
Scaling MySQL: Catch 22 of Read Write SplittingScaling MySQL: Catch 22 of Read Write Splitting
Scaling MySQL: Catch 22 of Read Write Splitting
 
Cars Final Report (2).ppt
Cars Final Report (2).pptCars Final Report (2).ppt
Cars Final Report (2).ppt
 
Dataiku r users group v2
Dataiku   r users group v2Dataiku   r users group v2
Dataiku r users group v2
 
The Road to Business Agility
The Road to Business AgilityThe Road to Business Agility
The Road to Business Agility
 
Teradata Big Data London Seminar
Teradata Big Data London SeminarTeradata Big Data London Seminar
Teradata Big Data London Seminar
 
Big Data: A Big Trap for Product Development
Big Data: A Big Trap for Product DevelopmentBig Data: A Big Trap for Product Development
Big Data: A Big Trap for Product Development
 
Module 3 Adapative Customer Experience Final
Module 3 Adapative Customer Experience FinalModule 3 Adapative Customer Experience Final
Module 3 Adapative Customer Experience Final
 
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOut
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOutScaleBase Webinar 8.16: ScaleUp vs. ScaleOut
ScaleBase Webinar 8.16: ScaleUp vs. ScaleOut
 
Big data meets big analytics
Big data meets big analyticsBig data meets big analytics
Big data meets big analytics
 
Process Steps
Process StepsProcess Steps
Process Steps
 
Information Management: Answering Today’s Enterprise Challenge
Information Management: Answering Today’s Enterprise ChallengeInformation Management: Answering Today’s Enterprise Challenge
Information Management: Answering Today’s Enterprise Challenge
 
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data
EDF2013: Selected Talk: Bryan Drexler: The 80/20 Rule and Big Data
 

Plus de Pivotal Analytics (Cetas Analytics)

Plus de Pivotal Analytics (Cetas Analytics) (8)

Gamification: Leveraging Game Strategies & Big Data to Drive Business with Dr...
Gamification: Leveraging Game Strategies & Big Data to Drive Business with Dr...Gamification: Leveraging Game Strategies & Big Data to Drive Business with Dr...
Gamification: Leveraging Game Strategies & Big Data to Drive Business with Dr...
 
Dr. Bob Hayes Big Data and the Total Customer Experience
Dr. Bob Hayes Big Data and the Total Customer ExperienceDr. Bob Hayes Big Data and the Total Customer Experience
Dr. Bob Hayes Big Data and the Total Customer Experience
 
Real-Time Customer Intelligence: The New Heartbeat for Growth and Profitability
Real-Time Customer Intelligence: The New Heartbeat for Growth and ProfitabilityReal-Time Customer Intelligence: The New Heartbeat for Growth and Profitability
Real-Time Customer Intelligence: The New Heartbeat for Growth and Profitability
 
Streaming Cloud Analytics: Enabling Dynamic Product Innovation From User Expe...
Streaming Cloud Analytics: Enabling Dynamic Product Innovation From User Expe...Streaming Cloud Analytics: Enabling Dynamic Product Innovation From User Expe...
Streaming Cloud Analytics: Enabling Dynamic Product Innovation From User Expe...
 
Wayne Eckerson: Secrets of Analytical Leaders
Wayne Eckerson: Secrets of Analytical LeadersWayne Eckerson: Secrets of Analytical Leaders
Wayne Eckerson: Secrets of Analytical Leaders
 
Laura Madsen Healthcare Business Intelligence & Big Data Analytics
Laura Madsen Healthcare Business Intelligence & Big Data AnalyticsLaura Madsen Healthcare Business Intelligence & Big Data Analytics
Laura Madsen Healthcare Business Intelligence & Big Data Analytics
 
Cetas Predictive Analytics Prezo
Cetas Predictive Analytics PrezoCetas Predictive Analytics Prezo
Cetas Predictive Analytics Prezo
 
Cetas Presentation at GigaOM Structure 2012
Cetas Presentation at GigaOM Structure 2012Cetas Presentation at GigaOM Structure 2012
Cetas Presentation at GigaOM Structure 2012
 

Dernier

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 

Dernier (20)

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 

Cetas Presentation on Real-time Recommendation Systems

  • 1. Real-Time Recommender Systems Bay Area Search Meetup at eBay April 25, 2012 Balu Rajagopal
  • 2. Goal of Recommenders INSTANT INTELLIGENCE 1. Increase number of items sold 2. Cross-Sell, Up-Sell diverse items 3. Increase Customer Satisfaction 4. Build Loyalty 5. Improve User Experience Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 2
  • 3. Recommendations INSTANT INTELLIGENCE USERS Search Recommendations Products Web sites Social networks ITEMS Blogs News …. Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 3
  • 4. Two Challenges INSTANT INTELLIGENCE  Make a Personalized Recommendation – Multi-Dimensional Data – Streams: Social, Activity, Apps, Tweets, Actions, … – Demographic – Temporal, Spatial  Do it in real-time – Query to Analysis to Visualization – User Experience (UX) – System Constraints – Network, Capacity, SLA Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 4
  • 5. Problem Space INSTANT INTELLIGENCE Cetas Instant Intelligence Framework Secs or Less Large RESPONSE TIME TO USER DATA DIMENSIONS Minutes Medium Hours Small Gigabytes Terabytes Petabytes ANALYSIS VOLUME Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 5
  • 6. Real-time Recommender System INSTANT INTELLIGENCE Inputs Terabytes of Multi-Dimensional data Preprocessing Reduction @ Scale @ Speed Analysis Classifying, Clustering Output Prediction, Recommendation Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 6
  • 7. Real-time Recommender System INSTANT INTELLIGENCE • Spatial Inputs • Temporal • Demographic • Personal • Psychographic • Behavioral Preprocessing Reduction Analysis Classifying, Clustering Output Predictions, Recommendations, Patterns Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 7
  • 8. Real-time Recommender System INSTANT INTELLIGENCE • Spatial Inputs • Temporal • Demographic • Personal • Psychographic • Behavioral • Distance Measures Preprocessing • Sampling • PCA • Dimensionality Reduction • SVD Analysis Classifying, Clustering Output Predictions, Recommendations, Patterns Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 8
  • 9. Real-time Recommender System INSTANT INTELLIGENCE • Spatial Inputs • Temporal • Demographic • Personal • Psychographic • Behavioral • Distance Measures Preprocessing • Sampling • PCA • Dimensionality Reduction • SVD • Predictors • Classification Analysis • Descriptors • Association • Clustering Output Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 9
  • 10. Real-time Recommender System INSTANT INTELLIGENCE • Spatial Inputs • Temporal • Demographic • Personal • Psychographic • Behavioral • Distance Measures Preprocessing • Sampling • PCA • Dimensionality Reduction • SVD • Predictors • Classification Analysis • Descriptors • Association • Clustering • Predictions Output • Recommendations • Patterns Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 10
  • 11. Big Data Analytics – eCommerce INSTANT INTELLIGENCE Input data Clustering Closed-loop Action User transactions live stream Product placement decision Demographics data stream Category, sub- category sorting Online app events stream New product Ad placement offering stream Other streams … Other actions … Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 11
  • 12. Real-time Stream Processing INSTANT INTELLIGENCE Billions of Events I n d e x CEP RAM Cache Joins RAM Disk Aggregates HBase HDFS Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 12
  • 13. Wrap-up INSTANT INTELLIGENCE  Personalized Recommendation Engine – Non-trivial – Focus on Specific Use Case  Real-time – Distributed Indexing – Pre-computation – Compact store (in memory, on disk) – Parallelization Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 13
  • 14. References INSTANT INTELLIGENCE  Mining Massive Datasets – Free eBook – Anand Rajaraman, Jeff Ullman – cs246.stanford.edu  Introduction to Data Mining – Tan, Steinback, Kumar  Introduction to Recommender Systems Handbook – Ricci, Rokach, Shapira Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 14
  • 15. INSTANT INTELLIGENCE Cetas Software Inc. – Copyright © 2012– CONFIDENTIAL – DO NOT DISTRIBUTE 15