SlideShare une entreprise Scribd logo
1  sur  25
Télécharger pour lire hors ligne
Welcome to:
Real-Time Optimization:
Putting Facebook User Attributes to Work
  - Going Beyond A/B Testing and User Segmentation
  - Optimizing Open Graph


Alan Avidan − Executive Director
alan@BeesAndPollen.com
@beesandpollen
We’ll Cover:
1. The Playground: Games/Apps/Campaigns
2. Which User Attributes Can You Use for Optimization?
3. Predictive Best-Fit Optimization, and How Does it Lift
   KPIs like Revenue, Virality, Engagement, Retention
4. Traditional Optimization Tools:
   Analytics, A/B Testing, User Segmentation
5. Open Graph Optimization with Predictive Best-Fit
• Lots of Successful Apps, Games and Campaigns with
  Millions of (Individual) Users
• Low Retention, Low %Pay, High User Acquisition Costs
• Notifications/Posts Can Become Spammy and Blocked
• KPIs Under Pressure – Need Lift - Perform or Perish!
• Vast Amounts of User Attributes
Terminology
 • Attributes
 • Elements (Events/Decision Points)
 • Options (Variants)



                        Low Range      High Range
User DNA - Attributes Sources
  Facebook attributes: Friends, Influence, Likes, Interests, Posts, Events, etc.


  Open Graph: scores, achievements, published stories, custom actions, etc.


      Behavioral attributes: level, spending, score, health, custom, etc.


              Session attributes: time of day, day, duration, etc.


      Geo-Demographic attributes: age, gender, education, country, etc.


               3rd Party attributes: income level, education, etc.
Predictive Best-Fit – Core Concepts




Predictive Best-Fit Algorithms Find Correlations
     Between User DNA and Conversions
           User Social, open-graph                    Predictive Best-Fit
                                     DNA Generation    Algorithm Real-
    User    and Behavioral Data
                                                         Time action
Traditional Optimization Technologies
 A Quick Tour
                   Analytics




    Segmentation               A/B Testing
A/B Testing
Define options   Split traffic   Measure results   Deploy winner   Max Result




                                                    high range
  Low range




  High range
A/B Testing – Bottom Line

     Upside
   • Conceptually simple and understandable
     Can achieve good results – up to a point



     Downside:
   • One-size-fits-all
   • Results may deteriorate over time
A Priori Segmentation
  Define segments   Define Options and rule   Result
                             base




                           Low range




                            high range
A Priori Segmentation
    Upside
  • Can be effective if segmentation was meaningful


    Downside
  • Segments are predefined and cannot be changed
    during the analysis
  • Different elements might require different segments
  • Hard to scale in terms of data-set and number of
    elements
  • Hard to fine-tune
Clustering Segmentation
  Define     A/B test   Segment users     Deploy winner
  options    options    based on result




Low
range




High range
Clustering Segmentation
     Upside:
   • Highest Lift
   • Discover correlations you never knew existed

     Downside:
   • Requires storage of terabytes of data
   • Need really smart people to work on it
   • Effort = Very High
Predictive Best-Fit
• Can optimize in-app and open graph performance
• Automated end-to-end solution
  (Acquire data, analyze, predict, enact)
• Machine self-learning
• Real-time
• No user history required
• Numerous data sources
• In full compliance with facebook privacy rules
• Deep new insights

                                    Effort/Resources
Elements For Predictive
Best-Fit Optimization
     Open Graph            Engagement            Retention
 •   Publish Yes/No?   •   Offers           •   Email
 •   Timing            •   Products         •   Message Timing
 •   Art and Copy      •   Content          •   Incentives
 •   Call-to-Action    •   Communications   •   Gifts
 •   Story


        Virality           Look & Feel          Monetization
 • Share Messages      • Colors             • Payment Page:
 • Invite Friends      • Graphics             Ranges, Incentives
                       • Layouts            • Shop Order
Open Graph     Big Impact
        SongPop Hits Major Milestones Just Three Months After Launch
        • 25 Million unique players to date
        • Has consistently received a coveted 5 start rating
        • 4 million people play every day, and growing
         Ford created an app that publish a story each time a user
         customized his dream Mustang and then battle others’ model.
         Although their goal was 2 million engagement they had more than
         5 millions and more than 17,000 referrals.

         Since revamping Open Graph stories with custom art and content,
         BINGO Blitz got 20% more likes and comments on news feed
         stories and 500% more unique clicks to the game.


         The food finding and sharing app has seen a 3X increase in number
         of visits and activities shared by helping people share the dishes
         they want, try and ate with friends on Facebook
Open Graph             Optimizations

  1                                                                               2
              3             4
                            5




                                                               6



  1                                 2           3              4
      Publish by User – Yes/No          Story       Image          Landing Page

                       5                            6
                           Action Verb Object           Time
Open Graph      1   Publish by User – Yes/No




                    Yes                        No




             Publish only by the right users!
Open Graph       2   Story




Post with the right content to engage the viewer

• Publish achievements the player unlocked
• Publish scores the player achieved
• Publish custom activities:
  Jeff E. finished Level 4 on MyGame!
• Publish extended custom activities:
  Jeff E. won a game against Chris on MyGame!
Open Graph         3   Image




       Option A                                Option A
       Image of song, leading to               Image taken from to
       clip                                    game

       Option B                                Option B
       Image of genre, leading                 Image of real-world
       friends to songs/albums                 landscape
       recently listened to by user




          Publish using the most effective creative
Open Graph         4   Landing Page




     Option A
     Landing page with the song playing

     Option B
     Landing page with the latest songs of that genre listened by
     friends’
     Option C
     Landing page of that album with a discount coupon


     Publish with the best landing page to convert the viewer
Open Graph         5   Action Verb Object




                                listen




    Option A
    Justin listened to [SONG X] by [SINGER-NAME] on Spotify

     Option B
     Justin listened to Classic [GENRE Y] music on Spotify

        Publish the most effective actions and objects
Open Graph       6   Timing




      Publish at the right time to get maximal exposure
                      Friends newsfeeds
The Last Word


Consider optimization if you wish to
become successful or stay relevant

Consider Predictive Best-Fit Optimization
All the Gain without the Pain
Welcome to:
 Real-Time Optimization:
 Putting Facebook User Attributes to Work
    - Going Beyond A/B Testing and User Segmentation
    - Optimizing Open Graph

Alan Avidan − Executive Director, Business Development
alan@BeesAndPollen.com
@beesandpollen

Contenu connexe

Tendances

Your YouTube Strategy Is Boring. Let's Fix It!
Your YouTube Strategy Is Boring. Let's Fix It!Your YouTube Strategy Is Boring. Let's Fix It!
Your YouTube Strategy Is Boring. Let's Fix It!Joe Martinez
 
OfferPop - Social Media Opportunities
OfferPop - Social Media OpportunitiesOfferPop - Social Media Opportunities
OfferPop - Social Media OpportunitiesHILMarketing
 
Using Imagery and Dynamic Media to Master User Experience
Using Imagery and Dynamic Media to Master User ExperienceUsing Imagery and Dynamic Media to Master User Experience
Using Imagery and Dynamic Media to Master User ExperienceMolly Pfister
 
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...Reynolds Journalism Institute (RJI)
 

Tendances (6)

Your YouTube Strategy Is Boring. Let's Fix It!
Your YouTube Strategy Is Boring. Let's Fix It!Your YouTube Strategy Is Boring. Let's Fix It!
Your YouTube Strategy Is Boring. Let's Fix It!
 
YouTube @ oi15
YouTube @ oi15YouTube @ oi15
YouTube @ oi15
 
OfferPop - Social Media Opportunities
OfferPop - Social Media OpportunitiesOfferPop - Social Media Opportunities
OfferPop - Social Media Opportunities
 
Using Imagery and Dynamic Media to Master User Experience
Using Imagery and Dynamic Media to Master User ExperienceUsing Imagery and Dynamic Media to Master User Experience
Using Imagery and Dynamic Media to Master User Experience
 
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...
Jigar Mehta and Kevin Dubouis: Video as a building block for engagement, loya...
 
Social Media
Social MediaSocial Media
Social Media
 

En vedette

Day1 1300 melnick_beyond performance marketing
Day1 1300 melnick_beyond performance marketingDay1 1300 melnick_beyond performance marketing
Day1 1300 melnick_beyond performance marketingMediabistro
 
Richard Firminger
Richard FirmingerRichard Firminger
Richard FirmingerMediabistro
 
Social Gaming & Gambling Summit - London Chris Anderson
Social Gaming & Gambling Summit - London Chris AndersonSocial Gaming & Gambling Summit - London Chris Anderson
Social Gaming & Gambling Summit - London Chris AndersonMediabistro
 
Tastemaking Through Curated Communities
Tastemaking Through Curated CommunitiesTastemaking Through Curated Communities
Tastemaking Through Curated CommunitiesMediabistro
 
Kelvin Wee_Inside 3D Printing Melbourne 2014
Kelvin Wee_Inside 3D Printing Melbourne 2014Kelvin Wee_Inside 3D Printing Melbourne 2014
Kelvin Wee_Inside 3D Printing Melbourne 2014Mediabistro
 

En vedette (8)

Day1 1300 melnick_beyond performance marketing
Day1 1300 melnick_beyond performance marketingDay1 1300 melnick_beyond performance marketing
Day1 1300 melnick_beyond performance marketing
 
Richard Firminger
Richard FirmingerRichard Firminger
Richard Firminger
 
Social Gaming & Gambling Summit - London Chris Anderson
Social Gaming & Gambling Summit - London Chris AndersonSocial Gaming & Gambling Summit - London Chris Anderson
Social Gaming & Gambling Summit - London Chris Anderson
 
Tastemaking Through Curated Communities
Tastemaking Through Curated CommunitiesTastemaking Through Curated Communities
Tastemaking Through Curated Communities
 
Emeric Ernoult
Emeric ErnoultEmeric Ernoult
Emeric Ernoult
 
Sudha Jamthe
Sudha JamtheSudha Jamthe
Sudha Jamthe
 
Kelvin Wee_Inside 3D Printing Melbourne 2014
Kelvin Wee_Inside 3D Printing Melbourne 2014Kelvin Wee_Inside 3D Printing Melbourne 2014
Kelvin Wee_Inside 3D Printing Melbourne 2014
 
Eric Ludwig
Eric LudwigEric Ludwig
Eric Ludwig
 

Similaire à Alan Avidan

AB Testing Your Way to a Successful Website, Email, Social Media
AB Testing Your Way to a Successful Website, Email, Social MediaAB Testing Your Way to a Successful Website, Email, Social Media
AB Testing Your Way to a Successful Website, Email, Social MediaDevon Smith
 
Merkle - iStrategy Chicago
Merkle - iStrategy ChicagoMerkle - iStrategy Chicago
Merkle - iStrategy ChicagoiStrategy
 
What the new Facebook means for Brands
What the new Facebook means for BrandsWhat the new Facebook means for Brands
What the new Facebook means for BrandsBramerz
 
Resgrid Pitch Deck
Resgrid Pitch DeckResgrid Pitch Deck
Resgrid Pitch DeckResgrid
 
Meeting my aims objectives - survey results
Meeting my aims objectives - survey resultsMeeting my aims objectives - survey results
Meeting my aims objectives - survey resultsHayley Ip
 
Building A Product People Love - Yaron Samid - April 21, 2017
Building A Product People Love  - Yaron Samid - April 21, 2017Building A Product People Love  - Yaron Samid - April 21, 2017
Building A Product People Love - Yaron Samid - April 21, 2017Yaron Samid
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Ernesto Mislej
 
DeepakRawat_APMF.pdf
DeepakRawat_APMF.pdfDeepakRawat_APMF.pdf
DeepakRawat_APMF.pdfDeepak Rawat
 
Advanced Social Media - AAM Philadelphia
Advanced Social Media  - AAM PhiladelphiaAdvanced Social Media  - AAM Philadelphia
Advanced Social Media - AAM PhiladelphiaJessica Levin
 
Business Insider, Social Commerce Summit, Offerpop
Business Insider, Social Commerce Summit, OfferpopBusiness Insider, Social Commerce Summit, Offerpop
Business Insider, Social Commerce Summit, OfferpopJulie Hansen
 
When Search and Social Collide
When Search and Social CollideWhen Search and Social Collide
When Search and Social CollideInnoTech
 
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014Allet Douma
 
Yrals Digital Marketing - Product Suite
Yrals Digital Marketing - Product SuiteYrals Digital Marketing - Product Suite
Yrals Digital Marketing - Product SuiteRochelle Pereira
 
"How to Mobilize your Event & Take it to the Next Level"
"How to Mobilize your Event & Take it to the Next Level" "How to Mobilize your Event & Take it to the Next Level"
"How to Mobilize your Event & Take it to the Next Level" TheAppLabb
 
Foundations of a Successful Social Media Strategy
Foundations of a Successful Social Media Strategy Foundations of a Successful Social Media Strategy
Foundations of a Successful Social Media Strategy Erica Campbell Byrum
 
Graphics101
Graphics101Graphics101
Graphics101bthat
 
Selling UX in Your Organization - Stir Trek 2012
Selling UX in Your Organization - Stir Trek 2012Selling UX in Your Organization - Stir Trek 2012
Selling UX in Your Organization - Stir Trek 2012Carol Smith
 

Similaire à Alan Avidan (20)

AB Testing Your Way to a Successful Website, Email, Social Media
AB Testing Your Way to a Successful Website, Email, Social MediaAB Testing Your Way to a Successful Website, Email, Social Media
AB Testing Your Way to a Successful Website, Email, Social Media
 
Facebook Open Graph
Facebook Open GraphFacebook Open Graph
Facebook Open Graph
 
Merkle - iStrategy Chicago
Merkle - iStrategy ChicagoMerkle - iStrategy Chicago
Merkle - iStrategy Chicago
 
What the new Facebook means for Brands
What the new Facebook means for BrandsWhat the new Facebook means for Brands
What the new Facebook means for Brands
 
Resgrid Pitch Deck
Resgrid Pitch DeckResgrid Pitch Deck
Resgrid Pitch Deck
 
Meeting my aims objectives - survey results
Meeting my aims objectives - survey resultsMeeting my aims objectives - survey results
Meeting my aims objectives - survey results
 
Building A Product People Love - Yaron Samid - April 21, 2017
Building A Product People Love  - Yaron Samid - April 21, 2017Building A Product People Love  - Yaron Samid - April 21, 2017
Building A Product People Love - Yaron Samid - April 21, 2017
 
Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011Recommender Systems! @ASAI 2011
Recommender Systems! @ASAI 2011
 
Oap final
Oap finalOap final
Oap final
 
How to use facebook for business
How to use facebook for businessHow to use facebook for business
How to use facebook for business
 
DeepakRawat_APMF.pdf
DeepakRawat_APMF.pdfDeepakRawat_APMF.pdf
DeepakRawat_APMF.pdf
 
Advanced Social Media - AAM Philadelphia
Advanced Social Media  - AAM PhiladelphiaAdvanced Social Media  - AAM Philadelphia
Advanced Social Media - AAM Philadelphia
 
Business Insider, Social Commerce Summit, Offerpop
Business Insider, Social Commerce Summit, OfferpopBusiness Insider, Social Commerce Summit, Offerpop
Business Insider, Social Commerce Summit, Offerpop
 
When Search and Social Collide
When Search and Social CollideWhen Search and Social Collide
When Search and Social Collide
 
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014
Presentatie Kate Russel - Mediafacts Nationale Uitgeefdag 2014
 
Yrals Digital Marketing - Product Suite
Yrals Digital Marketing - Product SuiteYrals Digital Marketing - Product Suite
Yrals Digital Marketing - Product Suite
 
"How to Mobilize your Event & Take it to the Next Level"
"How to Mobilize your Event & Take it to the Next Level" "How to Mobilize your Event & Take it to the Next Level"
"How to Mobilize your Event & Take it to the Next Level"
 
Foundations of a Successful Social Media Strategy
Foundations of a Successful Social Media Strategy Foundations of a Successful Social Media Strategy
Foundations of a Successful Social Media Strategy
 
Graphics101
Graphics101Graphics101
Graphics101
 
Selling UX in Your Organization - Stir Trek 2012
Selling UX in Your Organization - Stir Trek 2012Selling UX in Your Organization - Stir Trek 2012
Selling UX in Your Organization - Stir Trek 2012
 

Plus de Mediabistro

Elements of a Successful Job Listing
Elements of a Successful Job ListingElements of a Successful Job Listing
Elements of a Successful Job ListingMediabistro
 
Kelvin Wee_Inszi
Kelvin Wee_InsziKelvin Wee_Inszi
Kelvin Wee_InsziMediabistro
 
Paul Taylor_Inside 3D Printing Melbourne
Paul Taylor_Inside 3D Printing MelbournePaul Taylor_Inside 3D Printing Melbourne
Paul Taylor_Inside 3D Printing MelbourneMediabistro
 
Paul Mignone_Inside 3D Printing Melbourne
Paul Mignone_Inside 3D Printing MelbournePaul Mignone_Inside 3D Printing Melbourne
Paul Mignone_Inside 3D Printing MelbourneMediabistro
 
Angela Daly_Inside 3D Printing Melbourne
Angela Daly_Inside 3D Printing MelbourneAngela Daly_Inside 3D Printing Melbourne
Angela Daly_Inside 3D Printing MelbourneMediabistro
 
Chris Leigh-Lancaster_Inside 3D Printing Melbourne
Chris Leigh-Lancaster_Inside 3D Printing MelbourneChris Leigh-Lancaster_Inside 3D Printing Melbourne
Chris Leigh-Lancaster_Inside 3D Printing MelbourneMediabistro
 
Terry Wohlers_Inside 3D Printing Melbourne
Terry Wohlers_Inside 3D Printing MelbourneTerry Wohlers_Inside 3D Printing Melbourne
Terry Wohlers_Inside 3D Printing MelbourneMediabistro
 
2014 07-09 Juan Llanos Presentation
2014 07-09 Juan Llanos Presentation2014 07-09 Juan Llanos Presentation
2014 07-09 Juan Llanos PresentationMediabistro
 
Gary Anderson_Inside 3D Printing Melbourne
Gary Anderson_Inside 3D Printing MelbourneGary Anderson_Inside 3D Printing Melbourne
Gary Anderson_Inside 3D Printing MelbourneMediabistro
 
James canning inside bitcoin melbourne final
James canning inside bitcoin melbourne finalJames canning inside bitcoin melbourne final
James canning inside bitcoin melbourne finalMediabistro
 
Gst & bitcoins slides- Potential Pitfalls
Gst & bitcoins slides- Potential PitfallsGst & bitcoins slides- Potential Pitfalls
Gst & bitcoins slides- Potential PitfallsMediabistro
 
Building a trading platform from scratch
Building a trading platform from scratchBuilding a trading platform from scratch
Building a trading platform from scratchMediabistro
 
Bitcoin Lateral Economics
Bitcoin Lateral EconomicsBitcoin Lateral Economics
Bitcoin Lateral EconomicsMediabistro
 
State of Ethereum, and Mining
State of Ethereum, and MiningState of Ethereum, and Mining
State of Ethereum, and MiningMediabistro
 
Future of Bitcoin Mining- Josh Zerlan
Future of Bitcoin Mining- Josh ZerlanFuture of Bitcoin Mining- Josh Zerlan
Future of Bitcoin Mining- Josh ZerlanMediabistro
 
Evan Wagner and Robby Dermody Presentation
Evan Wagner and Robby Dermody PresentationEvan Wagner and Robby Dermody Presentation
Evan Wagner and Robby Dermody PresentationMediabistro
 
Morning Keynote: Bobby Lee
Morning Keynote: Bobby LeeMorning Keynote: Bobby Lee
Morning Keynote: Bobby LeeMediabistro
 
Yuan Bao Presentation
Yuan Bao PresentationYuan Bao Presentation
Yuan Bao PresentationMediabistro
 

Plus de Mediabistro (20)

Elements of a Successful Job Listing
Elements of a Successful Job ListingElements of a Successful Job Listing
Elements of a Successful Job Listing
 
Kelvin Wee_Inszi
Kelvin Wee_InsziKelvin Wee_Inszi
Kelvin Wee_Inszi
 
Melb oleg2
Melb oleg2Melb oleg2
Melb oleg2
 
Paul Taylor_Inside 3D Printing Melbourne
Paul Taylor_Inside 3D Printing MelbournePaul Taylor_Inside 3D Printing Melbourne
Paul Taylor_Inside 3D Printing Melbourne
 
Paul Mignone_Inside 3D Printing Melbourne
Paul Mignone_Inside 3D Printing MelbournePaul Mignone_Inside 3D Printing Melbourne
Paul Mignone_Inside 3D Printing Melbourne
 
Angela Daly_Inside 3D Printing Melbourne
Angela Daly_Inside 3D Printing MelbourneAngela Daly_Inside 3D Printing Melbourne
Angela Daly_Inside 3D Printing Melbourne
 
Chris Leigh-Lancaster_Inside 3D Printing Melbourne
Chris Leigh-Lancaster_Inside 3D Printing MelbourneChris Leigh-Lancaster_Inside 3D Printing Melbourne
Chris Leigh-Lancaster_Inside 3D Printing Melbourne
 
Terry Wohlers_Inside 3D Printing Melbourne
Terry Wohlers_Inside 3D Printing MelbourneTerry Wohlers_Inside 3D Printing Melbourne
Terry Wohlers_Inside 3D Printing Melbourne
 
2014 07-09 Juan Llanos Presentation
2014 07-09 Juan Llanos Presentation2014 07-09 Juan Llanos Presentation
2014 07-09 Juan Llanos Presentation
 
Gary Anderson_Inside 3D Printing Melbourne
Gary Anderson_Inside 3D Printing MelbourneGary Anderson_Inside 3D Printing Melbourne
Gary Anderson_Inside 3D Printing Melbourne
 
James canning inside bitcoin melbourne final
James canning inside bitcoin melbourne finalJames canning inside bitcoin melbourne final
James canning inside bitcoin melbourne final
 
Gst & bitcoins slides- Potential Pitfalls
Gst & bitcoins slides- Potential PitfallsGst & bitcoins slides- Potential Pitfalls
Gst & bitcoins slides- Potential Pitfalls
 
Building a trading platform from scratch
Building a trading platform from scratchBuilding a trading platform from scratch
Building a trading platform from scratch
 
Bitcoin Lateral Economics
Bitcoin Lateral EconomicsBitcoin Lateral Economics
Bitcoin Lateral Economics
 
State of Ethereum, and Mining
State of Ethereum, and MiningState of Ethereum, and Mining
State of Ethereum, and Mining
 
Future of Bitcoin Mining- Josh Zerlan
Future of Bitcoin Mining- Josh ZerlanFuture of Bitcoin Mining- Josh Zerlan
Future of Bitcoin Mining- Josh Zerlan
 
Evan Wagner and Robby Dermody Presentation
Evan Wagner and Robby Dermody PresentationEvan Wagner and Robby Dermody Presentation
Evan Wagner and Robby Dermody Presentation
 
Crypto Law
Crypto LawCrypto Law
Crypto Law
 
Morning Keynote: Bobby Lee
Morning Keynote: Bobby LeeMorning Keynote: Bobby Lee
Morning Keynote: Bobby Lee
 
Yuan Bao Presentation
Yuan Bao PresentationYuan Bao Presentation
Yuan Bao Presentation
 

Alan Avidan

  • 1. Welcome to: Real-Time Optimization: Putting Facebook User Attributes to Work - Going Beyond A/B Testing and User Segmentation - Optimizing Open Graph Alan Avidan − Executive Director alan@BeesAndPollen.com @beesandpollen
  • 2. We’ll Cover: 1. The Playground: Games/Apps/Campaigns 2. Which User Attributes Can You Use for Optimization? 3. Predictive Best-Fit Optimization, and How Does it Lift KPIs like Revenue, Virality, Engagement, Retention 4. Traditional Optimization Tools: Analytics, A/B Testing, User Segmentation 5. Open Graph Optimization with Predictive Best-Fit
  • 3. • Lots of Successful Apps, Games and Campaigns with Millions of (Individual) Users • Low Retention, Low %Pay, High User Acquisition Costs • Notifications/Posts Can Become Spammy and Blocked • KPIs Under Pressure – Need Lift - Perform or Perish! • Vast Amounts of User Attributes
  • 4. Terminology • Attributes • Elements (Events/Decision Points) • Options (Variants) Low Range High Range
  • 5. User DNA - Attributes Sources Facebook attributes: Friends, Influence, Likes, Interests, Posts, Events, etc. Open Graph: scores, achievements, published stories, custom actions, etc. Behavioral attributes: level, spending, score, health, custom, etc. Session attributes: time of day, day, duration, etc. Geo-Demographic attributes: age, gender, education, country, etc. 3rd Party attributes: income level, education, etc.
  • 6. Predictive Best-Fit – Core Concepts Predictive Best-Fit Algorithms Find Correlations Between User DNA and Conversions User Social, open-graph Predictive Best-Fit DNA Generation Algorithm Real- User and Behavioral Data Time action
  • 7. Traditional Optimization Technologies A Quick Tour Analytics Segmentation A/B Testing
  • 8. A/B Testing Define options Split traffic Measure results Deploy winner Max Result high range Low range High range
  • 9. A/B Testing – Bottom Line Upside • Conceptually simple and understandable Can achieve good results – up to a point Downside: • One-size-fits-all • Results may deteriorate over time
  • 10. A Priori Segmentation Define segments Define Options and rule Result base Low range high range
  • 11. A Priori Segmentation Upside • Can be effective if segmentation was meaningful Downside • Segments are predefined and cannot be changed during the analysis • Different elements might require different segments • Hard to scale in terms of data-set and number of elements • Hard to fine-tune
  • 12. Clustering Segmentation Define A/B test Segment users Deploy winner options options based on result Low range High range
  • 13. Clustering Segmentation Upside: • Highest Lift • Discover correlations you never knew existed Downside: • Requires storage of terabytes of data • Need really smart people to work on it • Effort = Very High
  • 14. Predictive Best-Fit • Can optimize in-app and open graph performance • Automated end-to-end solution (Acquire data, analyze, predict, enact) • Machine self-learning • Real-time • No user history required • Numerous data sources • In full compliance with facebook privacy rules • Deep new insights Effort/Resources
  • 15. Elements For Predictive Best-Fit Optimization Open Graph Engagement Retention • Publish Yes/No? • Offers • Email • Timing • Products • Message Timing • Art and Copy • Content • Incentives • Call-to-Action • Communications • Gifts • Story Virality Look & Feel Monetization • Share Messages • Colors • Payment Page: • Invite Friends • Graphics Ranges, Incentives • Layouts • Shop Order
  • 16. Open Graph Big Impact SongPop Hits Major Milestones Just Three Months After Launch • 25 Million unique players to date • Has consistently received a coveted 5 start rating • 4 million people play every day, and growing Ford created an app that publish a story each time a user customized his dream Mustang and then battle others’ model. Although their goal was 2 million engagement they had more than 5 millions and more than 17,000 referrals. Since revamping Open Graph stories with custom art and content, BINGO Blitz got 20% more likes and comments on news feed stories and 500% more unique clicks to the game. The food finding and sharing app has seen a 3X increase in number of visits and activities shared by helping people share the dishes they want, try and ate with friends on Facebook
  • 17. Open Graph Optimizations 1 2 3 4 5 6 1 2 3 4 Publish by User – Yes/No Story Image Landing Page 5 6 Action Verb Object Time
  • 18. Open Graph 1 Publish by User – Yes/No Yes No Publish only by the right users!
  • 19. Open Graph 2 Story Post with the right content to engage the viewer • Publish achievements the player unlocked • Publish scores the player achieved • Publish custom activities: Jeff E. finished Level 4 on MyGame! • Publish extended custom activities: Jeff E. won a game against Chris on MyGame!
  • 20. Open Graph 3 Image Option A Option A Image of song, leading to Image taken from to clip game Option B Option B Image of genre, leading Image of real-world friends to songs/albums landscape recently listened to by user Publish using the most effective creative
  • 21. Open Graph 4 Landing Page Option A Landing page with the song playing Option B Landing page with the latest songs of that genre listened by friends’ Option C Landing page of that album with a discount coupon Publish with the best landing page to convert the viewer
  • 22. Open Graph 5 Action Verb Object listen Option A Justin listened to [SONG X] by [SINGER-NAME] on Spotify Option B Justin listened to Classic [GENRE Y] music on Spotify Publish the most effective actions and objects
  • 23. Open Graph 6 Timing Publish at the right time to get maximal exposure Friends newsfeeds
  • 24. The Last Word Consider optimization if you wish to become successful or stay relevant Consider Predictive Best-Fit Optimization All the Gain without the Pain
  • 25. Welcome to: Real-Time Optimization: Putting Facebook User Attributes to Work - Going Beyond A/B Testing and User Segmentation - Optimizing Open Graph Alan Avidan − Executive Director, Business Development alan@BeesAndPollen.com @beesandpollen