SlideShare a Scribd company logo
1 of 57
Data Science of Love
The eHarmony Difference ›   Who we are




             ~45% Tech
The eHarmony Difference ›   Who we are




             ~45% Tech




             ~15% Customer Care
The eHarmony Difference ›     Who we are




             ~45% Tech




             ~15% Customer Care



             ~10% Marketing
The eHarmony Difference ›   Compatibility Matching System®
The eHarmony Difference ›   Compatibility Matching System®




                              Compatibility Matching
                              System®
The eHarmony Difference ›   Compatibility Matching System®




                              Compatibility Matching
                              System®




       1
  Compatibility
   Matching
The eHarmony Difference ›      Compatibility Matching System®




                                 Compatibility Matching
                                 System®




       1              2
  Compatibility     Affinity
   Matching        Matching
The eHarmony Difference ›      Compatibility Matching System®




                                 Compatibility Matching
                                 System®




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
The eHarmony Difference
The eHarmony Difference ›      Compatibility Matching System®




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
The eHarmony Difference ›      Compatibility Matching System®




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
Compatibility Matching ›   Relationship Questionnaire




                                 ›   Personality
                                 ›   Values
                                 ›   Attitudes
                                 ›   Beliefs
Compatibility Matching ›   Obstreperousness
Compatibility Matching ›   Romantic
Compatibility Matching ›   29 Dimensions®
Compatibility Matching ›   29 Dimensions®
The eHarmony Difference ›      Compatibility Matching System®




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
The eHarmony Difference ›      Compatibility Matching System®




                                  Layers on Top of
                                  Compatibility Matching




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
Affinity Matching ›
Affinity Matching ›


                  61   21
Affinity Matching ›


                  61          21




                       3000
Affinity Matching ›


                  61          21




                       3000
Affinity Matching ›
Affinity Matching ›




             …        …   …
Affinity Matching ›   Distance




                        Prob(	
  	
  	
  	
  	
  	
  	
  )
Affinity Matching ›   Distance
Affinity Matching ›                  Height difference




Prob(	
  	
  	
  	
  	
  	
  	
  )            4	
  -­‐	
  8	
  in




                                                                    cm
Affinity Matching ›                  “Attractiveness”




Prob(	
  	
  	
  	
  	
  	
  	
  )
Affinity Matching ›   Zoom level
Affinity Matching ›   Zoom level
Affinity Matching ›   Zoom level
Affinity Matching ›           Food preference




            25%       -­‐1%         -­‐24%      20%      13%


             9%       -­‐5%         -­‐27%       7%       0%


            -­‐12%    -­‐21%      -­‐42%        -­‐19%   -­‐23%


            19%        0%           -­‐28%      28%      10%


             9%       -­‐11%        -­‐35%      11%      44%
Affinity Matching ›           Food preference




            25%       -­‐1%         -­‐24%      20%      13%


             9%       -­‐5%         -­‐27%       7%       0%


            -­‐12%    -­‐21%        -­‐42%      -­‐19%   -­‐23%


            19%        0%           -­‐28%      28%      10%


             9%       -­‐11%        -­‐35%      11%      44%
Affinity Matching ›              Prob(   | data)



~40M	
  registered	
  users

                           ...

                           ...




                ~10^3	
  aCributes




                                                        ?
~10^8	
  matches	
  per	
  day
                                                   ~10^8	
  daily
Affinity Matching ›              Prob(       | data)



                                  data

  large	
  sparse	
  redundant           dense	
  complex	
  non-­‐linear	
  
            (freetext)                     moderate	
  #features




      vowpal	
  wabbit              gradient	
  boosted	
  decision	
  trees




                                  ?
Affinity Matching ›      Domain Specific Language




                                        ...
                 ...

                 ...
                                                    ??


                   DSL


        embarassingly	
  parallel
The eHarmony Difference ›      Compatibility Matching System®




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
The eHarmony Difference ›      Compatibility Matching System®




                                  Delivering the right
                                  matches at the right
                                  time to as many people
                                  as possible across the
                                  entire network.




       1              2                       3
  Compatibility     Affinity                 Match
   Matching        Matching               Distribution
Match Distribution ›   Graph optimization
Match Distribution ›   Graph optimization
Match Distribution ›   Graph optimization



       2                                    2
Match Distribution ›   Graph optimization



       2               1                    2
Match Distribution ›     Graph optimization



       2         Prob(   1 | data)            2
Match Distribution ›     Graph optimization



       2         Prob(   1 | data)            2
Match Distribution ›     Graph optimization



       2         Prob(      | data)           2
Match Distribution ›     Graph optimization



       2         Prob(      | data)           2
Guided
Resulting Customer Experience ›   Communication
Guided
Resulting Customer Experience ›   Communication
Guided
Resulting Customer Experience ›   Communication




                  ?      !
Resulting Customer Experience ›   Success!
Resulting Customer Experience ›   Success!
eHarmony Results ›    The eHarmony Impact




             2005


              90
              eHarmony Members
              Married Every Day *

                     * According to a Harris Interactive survey for eHarmony
eHarmony Results ›    The eHarmony Impact




             2005          2007


              236
              eHarmony Members
              Married Every Day *

                     * According to a Harris Interactive survey for eHarmony
eHarmony Results ›    The eHarmony Impact




             2005          2007                  2009


              542
              eHarmony Members
              Married Every Day *

                     * According to a Harris Interactive survey for eHarmony
@petricek   linkedin.com/in/petricek

More Related Content

Viewers also liked

Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...
Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...
Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...Engel Fonseca
 
Actividades marzo museo alhambra 2013
Actividades marzo museo alhambra 2013 Actividades marzo museo alhambra 2013
Actividades marzo museo alhambra 2013 Marcos Gutierrez
 
Simon decher & the secret formula
 Simon decher & the secret formula Simon decher & the secret formula
Simon decher & the secret formulaJenny Hidalgo
 
Dossier presentacion.sevillanas.indignadas
Dossier presentacion.sevillanas.indignadasDossier presentacion.sevillanas.indignadas
Dossier presentacion.sevillanas.indignadasTUCIUDAD
 
Joomla 1.7 Guia del Principiante
Joomla 1.7 Guia del PrincipianteJoomla 1.7 Guia del Principiante
Joomla 1.7 Guia del PrincipianteDigital Pymes
 
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...newreporter
 
Prefeitura do município de mirante da serra – ro
Prefeitura do município de mirante da serra – roPrefeitura do município de mirante da serra – ro
Prefeitura do município de mirante da serra – roOS CONCURSEIROS DE RONDÔNIA
 
Descargar driver de lexmark x1250
Descargar driver de lexmark x1250Descargar driver de lexmark x1250
Descargar driver de lexmark x1250DriverdeImpresora
 
Netvalue Web Marketing Solutions
Netvalue Web Marketing SolutionsNetvalue Web Marketing Solutions
Netvalue Web Marketing SolutionsData For Business
 
Opmax Presentatie Social Media En Seo
Opmax Presentatie Social Media En SeoOpmax Presentatie Social Media En Seo
Opmax Presentatie Social Media En SeoMark Eurlings
 
Rendicion de cuentas cultura
Rendicion de cuentas culturaRendicion de cuentas cultura
Rendicion de cuentas culturaalbacress
 
Open atrium 2.0 at BADcamp
Open atrium 2.0 at BADcampOpen atrium 2.0 at BADcamp
Open atrium 2.0 at BADcampPhase2
 
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...elarcadelmisterio
 

Viewers also liked (18)

Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...
Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...
Oportunidades De Mkt PolíTico Digital Obama2.0 Comite Mkt Publicidad Amipci P...
 
Actividades marzo museo alhambra 2013
Actividades marzo museo alhambra 2013 Actividades marzo museo alhambra 2013
Actividades marzo museo alhambra 2013
 
Simon decher & the secret formula
 Simon decher & the secret formula Simon decher & the secret formula
Simon decher & the secret formula
 
Dossier presentacion.sevillanas.indignadas
Dossier presentacion.sevillanas.indignadasDossier presentacion.sevillanas.indignadas
Dossier presentacion.sevillanas.indignadas
 
Joomla 1.7 Guia del Principiante
Joomla 1.7 Guia del PrincipianteJoomla 1.7 Guia del Principiante
Joomla 1.7 Guia del Principiante
 
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...
'Monetization trends for the future of new media' Деннис Дж. Адамович, официа...
 
Prefeitura do município de mirante da serra – ro
Prefeitura do município de mirante da serra – roPrefeitura do município de mirante da serra – ro
Prefeitura do município de mirante da serra – ro
 
Descargar driver de lexmark x1250
Descargar driver de lexmark x1250Descargar driver de lexmark x1250
Descargar driver de lexmark x1250
 
Netvalue Web Marketing Solutions
Netvalue Web Marketing SolutionsNetvalue Web Marketing Solutions
Netvalue Web Marketing Solutions
 
Opmax Presentatie Social Media En Seo
Opmax Presentatie Social Media En SeoOpmax Presentatie Social Media En Seo
Opmax Presentatie Social Media En Seo
 
Deimos building control suite esp
Deimos building control suite espDeimos building control suite esp
Deimos building control suite esp
 
Rendicion de cuentas cultura
Rendicion de cuentas culturaRendicion de cuentas cultura
Rendicion de cuentas cultura
 
STSI HOLDING
STSI HOLDINGSTSI HOLDING
STSI HOLDING
 
8020 guarding flipbook
8020 guarding flipbook8020 guarding flipbook
8020 guarding flipbook
 
Open atrium 2.0 at BADcamp
Open atrium 2.0 at BADcampOpen atrium 2.0 at BADcamp
Open atrium 2.0 at BADcamp
 
LinkedIn Everywhere
LinkedIn EverywhereLinkedIn Everywhere
LinkedIn Everywhere
 
Kerchner1
Kerchner1Kerchner1
Kerchner1
 
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...
Ley fibonacci-schreiber-para-el-crecimiento-de-la-poblacion-de-vampiros-y-sus...
 

Recently uploaded

Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clashcharlottematthew16
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 

Recently uploaded (20)

Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time ClashPowerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 

Data Science of Love