SlideShare a Scribd company logo
Big Data @ PersuasionAPI


Maurits Kaptein
Co-founder / Chief Scientist Science Rockstars
www.persuasionapi.com
Big Data?
 Big data is not really defined.

 “Datasets that are larger than „common‟
 machines can handle”
What I will and won’t talk about
 Yes: What are the challenges that are
 associated with big data
 Yes: How did we solve them in PersuasionAPI
 (high level)

 No: Algorithms
 No: Infrastructure / Technical details
3 Key Challenges
•   Focus on meaningful data
    •   So much data, but which is useful?

•   Move from Analytics to Advice
    •   No reports in hindsight but direct responses

•   Inability to run analysis on all of the data
    •   Need for summaries / online learning
Challenge 1:
What is meaningful?
What is meaningful
 Depends obviously on what your aim is as a
 company.

 We help companies increase conversion
 (Click-through, sales, etc.)
Persuasion plays a big role:
6 Principles of Persuasion




                                    8

        8
Beta Launch presentations Q2 2012   8
Persuasion Online




        9
Beta Launch presentations Q2 2012   9
Should we use all the strategies we
can think off?

At the same time?
For the same product?
Comparing many strategies with
  single strategies
          3000
          2000
Density

          500 1000
          0




                     0.000   0.002   0.004               0.006   0.008   0.010

                                         Click probability
Should we use all the strategies
we can think of?

No, we are better of selecting a
specific one.
Should we use the same strategies
for everyone?
                  Strategies not equally
                  effective for
                  everyone?

                  Large differences
                  based on personality
                  traits
2 Scenarios:

                                     Average




                                                                                         Average
                                               Individuals                                         Individuals

         -                                                   +   -                                               +
                 Effect of using a strategy                          Effect of using a strategy




        14
Beta Launch presentations Q2 2012                                                                                    14
Should we use the same
strategies for everyone?

No, people are distinct in their
reactions to different strategies.
Challenge 1:
Meaningful data
 Identify Persuasive Strategies
 Select distinct strategies
 Adapt to individuals

 Data:
 { userId : “zcvx2312”, strategyId : 4,
 implementation: 32, estimatedSucces : 0.23,
 certainty : 0.013}
Challenge 2:
Moving from analysis to advice
Choose not to produce reports after
logging responses…

But rather summarize all the data
to be available for direct
recommendations.
Persuasion Profile:

             Normal Page:

             A1 (Scarcity):

             A2 (Authority):

             A3 (Consensus):
                                         Effect



         •A persuasion profile is a collection of the
         estimates of the effect of persuasion principles
         for each individual user


        19                                                  19
Beta Launch presentations Q2 2012
We log the success of each attempt

             Normal Page:

             A1 (Scarcity):

             A2 (Authority):

             A3 (Consensus):
                                                       Effect




         •      Based on the dynamic image and the link we can monitor the
                success of each page served to a user.
         •      We will keep updates of the average performance of your served
                page variations, and of the performance for each client.



        20                                                                       20
Beta Launch presentations Q2 2012
We improve the personal profile

             Normal Page:

             A1 (Scarcity):

             A2 (Authority):

             A3 (Consensus):
                                                                    Effect


         •      Based on the response of each client we will update our advice for that user
         •      The new advice is a combination of the response of that client, as well as that of
                other clients




        21                                                                                           21
Beta Launch presentations Q2 2012
User navigates, we improve
                   First page served:                  Second page served:             Third page served:

             Normal:                             Normal:                         Normal:

             A1:                                 A1:                             A1:

             A2:                                 A2:                             A2:

             A3:                                 A3:                             A3:
                                        Effect                          Effect                              Effect



                And so on, for each individual client...

                Real time analytics is most effective in predicting
                behavior



        22                                                                                                       22
Beta Launch presentations Q2 2012
Competing Principles




        23
Beta Launch presentations Q2 2012   23
Example of adjusted page


                                    1: Log Client ID (e.g. via
                                    dynamic image, cookie, etc)

                                     2. Link(s) to log success of
                                    the Sales Strategy

                                     3. Hooks to log non-
                                    responsiveness to a Sales
                                    Strategy




        24                                                          24
Beta Launch presentations Q2 2012
Challenge 2:
We provide “advice” stating which
Strategy to Use for your current
customer.

In between page views…
Challenge 3:
How do we deal with all the data?
Problem 1: Impossible fitting to all
of the data in memory
 Move fully to “online” learning:
   Handle datapoint for datapoint
   Do not focus on ( theta | data ) but rather on ( theta |
   prior(s) )
    • Summarize all meaningful info in the priors.
   Find out what data you need and don’t need to make
   an impact on the bottom line.
    • E.g. no demographic data
   Use M/R jobs for re-estimating
Problem 2: Individual level
estimates are needed fast
 Use hierarchical models:
   Aggregated level => Input for new users
   User level => Start model for known users
 Apply shrinkage
   Link the two levels
 Use user-level model in isolation if necessary
   Analytical updates thus very fast.
Challenge 3:
How do we deal with all the data:

Use online learning and split
different levels of the model
Results
          Slide with the
        Increase inexample through:
          towell email click
        (at the 5th reminder)
                                      >100%

        Increase in e-commerce revenue:   >25%


        30
Beta Launch presentations Q2 2012                30
My Big Data considerations:
 Focus on meaningful data: Persuasion at an
 individual level.
 Move from analytics to real time response:
 Provide real-time advice
 Inability to analyze all of the data: Use online
 learning and hierarchical models.
End.
 Thanks!

 Contact us at:
   maurits@sciencerockstars.com
   +31 621262211

   www.sciencerockstars.com

More Related Content

Similar to Big Data sessie Maurits Kaptein

Software Principles and Project Deadlines Don't have to be Polar Opposites.pdf
Software Principles and Project Deadlines Don't have to be Polar Opposites.pdfSoftware Principles and Project Deadlines Don't have to be Polar Opposites.pdf
Software Principles and Project Deadlines Don't have to be Polar Opposites.pdf
Craig Saunders
 
Five questions for Ogilvy
Five questions for OgilvyFive questions for Ogilvy
Five questions for Ogilvy
Science Rockstars on Slideshare
 
5 Questions about Persuasion Profiling
5 Questions about Persuasion Profiling5 Questions about Persuasion Profiling
5 Questions about Persuasion Profiling
Science Rockstars on Slideshare
 
Bigdata and Social Media Analytics
Bigdata and Social Media Analytics Bigdata and Social Media Analytics
Bigdata and Social Media Analytics Dillip kumar
 
Connecting the dots social media across the customer journey
Connecting the dots  social media across the customer journeyConnecting the dots  social media across the customer journey
Connecting the dots social media across the customer journey
Clicktools
 
DigitalOcean SaaS Webinar - Jake Levirne
DigitalOcean SaaS Webinar - Jake LevirneDigitalOcean SaaS Webinar - Jake Levirne
DigitalOcean SaaS Webinar - Jake Levirne
Jake Levirne
 
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
Etumos
 
Models collecting dust? How to transform your results from interesting to imp...
Models collecting dust? How to transform your results from interesting to imp...Models collecting dust? How to transform your results from interesting to imp...
Models collecting dust? How to transform your results from interesting to imp...
Decision Management Solutions
 
B2B Social Media Marketing
B2B Social Media MarketingB2B Social Media Marketing
B2B Social Media Marketing
BullsEye Internet Marketing
 
Visualizations that make an impact - see what s new in minitab statistical s...
Visualizations that make an impact  - see what s new in minitab statistical s...Visualizations that make an impact  - see what s new in minitab statistical s...
Visualizations that make an impact - see what s new in minitab statistical s...
Minitab, LLC
 
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
mapexpo
 
From BI to Predictive Analytics
From BI to Predictive AnalyticsFrom BI to Predictive Analytics
From BI to Predictive Analytics
Decision Management Solutions
 
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
Revolution Analytics
 
Case Study on Building Products
Case Study on Building ProductsCase Study on Building Products
Case Study on Building Products
Pragmatic Leaders
 
Social Networking Opportunity Workshop
Social Networking Opportunity WorkshopSocial Networking Opportunity Workshop
Social Networking Opportunity Workshop
HawkPartners
 
3 AI Mistakes to Avoid in a Recession
3 AI Mistakes to Avoid in a Recession3 AI Mistakes to Avoid in a Recession
3 AI Mistakes to Avoid in a Recession
kmuehmel
 
Project Management And The Major Areas Of Projects Management
Project Management And The Major Areas Of Projects ManagementProject Management And The Major Areas Of Projects Management
Project Management And The Major Areas Of Projects Management
Miles Priar
 
ITSM Conference, Dubai, UAE 2009
ITSM Conference, Dubai, UAE   2009ITSM Conference, Dubai, UAE   2009
ITSM Conference, Dubai, UAE 2009
Tariq Elsadik
 
How to Calculate the ROI of Social Media
How to Calculate the ROI of Social MediaHow to Calculate the ROI of Social Media
How to Calculate the ROI of Social Media
Dr Natalie Petouhoff
 

Similar to Big Data sessie Maurits Kaptein (20)

Software Principles and Project Deadlines Don't have to be Polar Opposites.pdf
Software Principles and Project Deadlines Don't have to be Polar Opposites.pdfSoftware Principles and Project Deadlines Don't have to be Polar Opposites.pdf
Software Principles and Project Deadlines Don't have to be Polar Opposites.pdf
 
Five questions for Ogilvy
Five questions for OgilvyFive questions for Ogilvy
Five questions for Ogilvy
 
5 Questions about Persuasion Profiling
5 Questions about Persuasion Profiling5 Questions about Persuasion Profiling
5 Questions about Persuasion Profiling
 
Bigdata and Social Media Analytics
Bigdata and Social Media Analytics Bigdata and Social Media Analytics
Bigdata and Social Media Analytics
 
Connecting the dots social media across the customer journey
Connecting the dots  social media across the customer journeyConnecting the dots  social media across the customer journey
Connecting the dots social media across the customer journey
 
VC M&E Module 1 - Clients of the M&E System
VC M&E Module 1 - Clients of the M&E SystemVC M&E Module 1 - Clients of the M&E System
VC M&E Module 1 - Clients of the M&E System
 
DigitalOcean SaaS Webinar - Jake Levirne
DigitalOcean SaaS Webinar - Jake LevirneDigitalOcean SaaS Webinar - Jake Levirne
DigitalOcean SaaS Webinar - Jake Levirne
 
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
Lead Scoring Reinvented (Edward Unthank, Adobe Marketo Summit)
 
Models collecting dust? How to transform your results from interesting to imp...
Models collecting dust? How to transform your results from interesting to imp...Models collecting dust? How to transform your results from interesting to imp...
Models collecting dust? How to transform your results from interesting to imp...
 
B2B Social Media Marketing
B2B Social Media MarketingB2B Social Media Marketing
B2B Social Media Marketing
 
Visualizations that make an impact - see what s new in minitab statistical s...
Visualizations that make an impact  - see what s new in minitab statistical s...Visualizations that make an impact  - see what s new in minitab statistical s...
Visualizations that make an impact - see what s new in minitab statistical s...
 
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
MAPexpo 2012 - James Griffin & Greg Daniels (SR7)
 
From BI to Predictive Analytics
From BI to Predictive AnalyticsFrom BI to Predictive Analytics
From BI to Predictive Analytics
 
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
Models Collecting Dust? How to Transform Your Results from Interesting to Imp...
 
Case Study on Building Products
Case Study on Building ProductsCase Study on Building Products
Case Study on Building Products
 
Social Networking Opportunity Workshop
Social Networking Opportunity WorkshopSocial Networking Opportunity Workshop
Social Networking Opportunity Workshop
 
3 AI Mistakes to Avoid in a Recession
3 AI Mistakes to Avoid in a Recession3 AI Mistakes to Avoid in a Recession
3 AI Mistakes to Avoid in a Recession
 
Project Management And The Major Areas Of Projects Management
Project Management And The Major Areas Of Projects ManagementProject Management And The Major Areas Of Projects Management
Project Management And The Major Areas Of Projects Management
 
ITSM Conference, Dubai, UAE 2009
ITSM Conference, Dubai, UAE   2009ITSM Conference, Dubai, UAE   2009
ITSM Conference, Dubai, UAE 2009
 
How to Calculate the ROI of Social Media
How to Calculate the ROI of Social MediaHow to Calculate the ROI of Social Media
How to Calculate the ROI of Social Media
 

More from Info.nl

Emerce Dare 2017 - Iskander Smit
Emerce Dare 2017 - Iskander SmitEmerce Dare 2017 - Iskander Smit
Emerce Dare 2017 - Iskander Smit
Info.nl
 
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
Info.nl
 
Voetbal International: bouwne aan een krachtig digitaal platform
Voetbal International: bouwne aan een krachtig digitaal platformVoetbal International: bouwne aan een krachtig digitaal platform
Voetbal International: bouwne aan een krachtig digitaal platform
Info.nl
 
IoT & The City - Iskander Smit
IoT & The City - Iskander SmitIoT & The City - Iskander Smit
IoT & The City - Iskander Smit
Info.nl
 
Stampions Cross Media Cafe
Stampions Cross Media CafeStampions Cross Media Cafe
Stampions Cross Media Cafe
Info.nl
 
Amsterdam Beacon Meetup II - Stampions
Amsterdam Beacon Meetup II - StampionsAmsterdam Beacon Meetup II - Stampions
Amsterdam Beacon Meetup II - Stampions
Info.nl
 
Hacking Heritage talks - Iskander Smit
Hacking Heritage talks - Iskander SmitHacking Heritage talks - Iskander Smit
Hacking Heritage talks - Iskander Smit
Info.nl
 
HRO WDKA Retail 2030 Iskander Smit Shopping 2020
HRO WDKA Retail 2030 Iskander Smit Shopping 2020HRO WDKA Retail 2030 Iskander Smit Shopping 2020
HRO WDKA Retail 2030 Iskander Smit Shopping 2020
Info.nl
 
Hack thevisual 2015 workshop
Hack thevisual 2015 workshopHack thevisual 2015 workshop
Hack thevisual 2015 workshop
Info.nl
 
ThingsCon 2015 workshop haptic interactions
ThingsCon 2015 workshop haptic interactionsThingsCon 2015 workshop haptic interactions
ThingsCon 2015 workshop haptic interactions
Info.nl
 
Emerging Trends from SXSW2015 - Iskander Smit
Emerging Trends from SXSW2015 - Iskander SmitEmerging Trends from SXSW2015 - Iskander Smit
Emerging Trends from SXSW2015 - Iskander Smit
Info.nl
 
Simplifying complexity with microservices - Remmelt Pit
Simplifying complexity with microservices - Remmelt PitSimplifying complexity with microservices - Remmelt Pit
Simplifying complexity with microservices - Remmelt Pit
Info.nl
 
HRO Emerging Media Iskander Smit
HRO Emerging Media Iskander SmitHRO Emerging Media Iskander Smit
HRO Emerging Media Iskander Smit
Info.nl
 
Holland Call Stampions eindpresentatie
Holland Call Stampions eindpresentatieHolland Call Stampions eindpresentatie
Holland Call Stampions eindpresentatieInfo.nl
 
OPENwear Iskander Smit on haptic interactions
OPENwear Iskander Smit on haptic interactionsOPENwear Iskander Smit on haptic interactions
OPENwear Iskander Smit on haptic interactions
Info.nl
 
ThingsConAMS Iskander Smit
ThingsConAMS Iskander SmitThingsConAMS Iskander Smit
ThingsConAMS Iskander Smit
Info.nl
 
Eday2014 Simplifying Complexity with Microservices
Eday2014 Simplifying Complexity with MicroservicesEday2014 Simplifying Complexity with Microservices
Eday2014 Simplifying Complexity with Microservices
Info.nl
 
Knowledge session Glass - Labs.info.nl - Iskander Smit
Knowledge session Glass - Labs.info.nl - Iskander SmitKnowledge session Glass - Labs.info.nl - Iskander Smit
Knowledge session Glass - Labs.info.nl - Iskander Smit
Info.nl
 
Magnolia CMS Conference - Info.nl
Magnolia CMS Conference - Info.nlMagnolia CMS Conference - Info.nl
Magnolia CMS Conference - Info.nl
Info.nl
 
Magnolia CMS - on Jelastic
Magnolia CMS - on JelasticMagnolia CMS - on Jelastic
Magnolia CMS - on Jelastic
Info.nl
 

More from Info.nl (20)

Emerce Dare 2017 - Iskander Smit
Emerce Dare 2017 - Iskander SmitEmerce Dare 2017 - Iskander Smit
Emerce Dare 2017 - Iskander Smit
 
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
Enriching Internet of Things through design thinking - Melanie Gorka (Design ...
 
Voetbal International: bouwne aan een krachtig digitaal platform
Voetbal International: bouwne aan een krachtig digitaal platformVoetbal International: bouwne aan een krachtig digitaal platform
Voetbal International: bouwne aan een krachtig digitaal platform
 
IoT & The City - Iskander Smit
IoT & The City - Iskander SmitIoT & The City - Iskander Smit
IoT & The City - Iskander Smit
 
Stampions Cross Media Cafe
Stampions Cross Media CafeStampions Cross Media Cafe
Stampions Cross Media Cafe
 
Amsterdam Beacon Meetup II - Stampions
Amsterdam Beacon Meetup II - StampionsAmsterdam Beacon Meetup II - Stampions
Amsterdam Beacon Meetup II - Stampions
 
Hacking Heritage talks - Iskander Smit
Hacking Heritage talks - Iskander SmitHacking Heritage talks - Iskander Smit
Hacking Heritage talks - Iskander Smit
 
HRO WDKA Retail 2030 Iskander Smit Shopping 2020
HRO WDKA Retail 2030 Iskander Smit Shopping 2020HRO WDKA Retail 2030 Iskander Smit Shopping 2020
HRO WDKA Retail 2030 Iskander Smit Shopping 2020
 
Hack thevisual 2015 workshop
Hack thevisual 2015 workshopHack thevisual 2015 workshop
Hack thevisual 2015 workshop
 
ThingsCon 2015 workshop haptic interactions
ThingsCon 2015 workshop haptic interactionsThingsCon 2015 workshop haptic interactions
ThingsCon 2015 workshop haptic interactions
 
Emerging Trends from SXSW2015 - Iskander Smit
Emerging Trends from SXSW2015 - Iskander SmitEmerging Trends from SXSW2015 - Iskander Smit
Emerging Trends from SXSW2015 - Iskander Smit
 
Simplifying complexity with microservices - Remmelt Pit
Simplifying complexity with microservices - Remmelt PitSimplifying complexity with microservices - Remmelt Pit
Simplifying complexity with microservices - Remmelt Pit
 
HRO Emerging Media Iskander Smit
HRO Emerging Media Iskander SmitHRO Emerging Media Iskander Smit
HRO Emerging Media Iskander Smit
 
Holland Call Stampions eindpresentatie
Holland Call Stampions eindpresentatieHolland Call Stampions eindpresentatie
Holland Call Stampions eindpresentatie
 
OPENwear Iskander Smit on haptic interactions
OPENwear Iskander Smit on haptic interactionsOPENwear Iskander Smit on haptic interactions
OPENwear Iskander Smit on haptic interactions
 
ThingsConAMS Iskander Smit
ThingsConAMS Iskander SmitThingsConAMS Iskander Smit
ThingsConAMS Iskander Smit
 
Eday2014 Simplifying Complexity with Microservices
Eday2014 Simplifying Complexity with MicroservicesEday2014 Simplifying Complexity with Microservices
Eday2014 Simplifying Complexity with Microservices
 
Knowledge session Glass - Labs.info.nl - Iskander Smit
Knowledge session Glass - Labs.info.nl - Iskander SmitKnowledge session Glass - Labs.info.nl - Iskander Smit
Knowledge session Glass - Labs.info.nl - Iskander Smit
 
Magnolia CMS Conference - Info.nl
Magnolia CMS Conference - Info.nlMagnolia CMS Conference - Info.nl
Magnolia CMS Conference - Info.nl
 
Magnolia CMS - on Jelastic
Magnolia CMS - on JelasticMagnolia CMS - on Jelastic
Magnolia CMS - on Jelastic
 

Recently uploaded

GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
Neo4j
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
DianaGray10
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
Octavian Nadolu
 
20240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 202420240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 2024
Matthew Sinclair
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
Kari Kakkonen
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
Neo4j
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
Neo4j
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
Kumud Singh
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
DianaGray10
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
KAMESHS29
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
DianaGray10
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
James Anderson
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
Aftab Hussain
 

Recently uploaded (20)

GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6UiPath Test Automation using UiPath Test Suite series, part 6
UiPath Test Automation using UiPath Test Suite series, part 6
 
Artificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopmentArtificial Intelligence for XMLDevelopment
Artificial Intelligence for XMLDevelopment
 
20240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 202420240609 QFM020 Irresponsible AI Reading List May 2024
20240609 QFM020 Irresponsible AI Reading List May 2024
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
 
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024GraphSummit Singapore | The Art of the  Possible with Graph - Q2 2024
GraphSummit Singapore | The Art of the Possible with Graph - Q2 2024
 
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
GraphSummit Singapore | Neo4j Product Vision & Roadmap - Q2 2024
 
Mind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AIMind map of terminologies used in context of Generative AI
Mind map of terminologies used in context of Generative AI
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1Communications Mining Series - Zero to Hero - Session 1
Communications Mining Series - Zero to Hero - Session 1
 
RESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for studentsRESUME BUILDER APPLICATION Project for students
RESUME BUILDER APPLICATION Project for students
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5UiPath Test Automation using UiPath Test Suite series, part 5
UiPath Test Automation using UiPath Test Suite series, part 5
 
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
Alt. GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using ...
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Removing Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software FuzzingRemoving Uninteresting Bytes in Software Fuzzing
Removing Uninteresting Bytes in Software Fuzzing
 

Big Data sessie Maurits Kaptein

  • 1. Big Data @ PersuasionAPI Maurits Kaptein Co-founder / Chief Scientist Science Rockstars www.persuasionapi.com
  • 2. Big Data? Big data is not really defined. “Datasets that are larger than „common‟ machines can handle”
  • 3. What I will and won’t talk about Yes: What are the challenges that are associated with big data Yes: How did we solve them in PersuasionAPI (high level) No: Algorithms No: Infrastructure / Technical details
  • 4. 3 Key Challenges • Focus on meaningful data • So much data, but which is useful? • Move from Analytics to Advice • No reports in hindsight but direct responses • Inability to run analysis on all of the data • Need for summaries / online learning
  • 5. Challenge 1: What is meaningful?
  • 6. What is meaningful Depends obviously on what your aim is as a company. We help companies increase conversion (Click-through, sales, etc.)
  • 7. Persuasion plays a big role:
  • 8. 6 Principles of Persuasion 8 8 Beta Launch presentations Q2 2012 8
  • 9. Persuasion Online 9 Beta Launch presentations Q2 2012 9
  • 10. Should we use all the strategies we can think off? At the same time? For the same product?
  • 11. Comparing many strategies with single strategies 3000 2000 Density 500 1000 0 0.000 0.002 0.004 0.006 0.008 0.010 Click probability
  • 12. Should we use all the strategies we can think of? No, we are better of selecting a specific one.
  • 13. Should we use the same strategies for everyone? Strategies not equally effective for everyone? Large differences based on personality traits
  • 14. 2 Scenarios: Average Average Individuals Individuals - + - + Effect of using a strategy Effect of using a strategy 14 Beta Launch presentations Q2 2012 14
  • 15. Should we use the same strategies for everyone? No, people are distinct in their reactions to different strategies.
  • 16. Challenge 1: Meaningful data Identify Persuasive Strategies Select distinct strategies Adapt to individuals Data: { userId : “zcvx2312”, strategyId : 4, implementation: 32, estimatedSucces : 0.23, certainty : 0.013}
  • 17. Challenge 2: Moving from analysis to advice
  • 18. Choose not to produce reports after logging responses… But rather summarize all the data to be available for direct recommendations.
  • 19. Persuasion Profile: Normal Page: A1 (Scarcity): A2 (Authority): A3 (Consensus): Effect •A persuasion profile is a collection of the estimates of the effect of persuasion principles for each individual user 19 19 Beta Launch presentations Q2 2012
  • 20. We log the success of each attempt Normal Page: A1 (Scarcity): A2 (Authority): A3 (Consensus): Effect • Based on the dynamic image and the link we can monitor the success of each page served to a user. • We will keep updates of the average performance of your served page variations, and of the performance for each client. 20 20 Beta Launch presentations Q2 2012
  • 21. We improve the personal profile Normal Page: A1 (Scarcity): A2 (Authority): A3 (Consensus): Effect • Based on the response of each client we will update our advice for that user • The new advice is a combination of the response of that client, as well as that of other clients 21 21 Beta Launch presentations Q2 2012
  • 22. User navigates, we improve First page served: Second page served: Third page served: Normal: Normal: Normal: A1: A1: A1: A2: A2: A2: A3: A3: A3: Effect Effect Effect And so on, for each individual client... Real time analytics is most effective in predicting behavior 22 22 Beta Launch presentations Q2 2012
  • 23. Competing Principles 23 Beta Launch presentations Q2 2012 23
  • 24. Example of adjusted page 1: Log Client ID (e.g. via dynamic image, cookie, etc) 2. Link(s) to log success of the Sales Strategy 3. Hooks to log non- responsiveness to a Sales Strategy 24 24 Beta Launch presentations Q2 2012
  • 25. Challenge 2: We provide “advice” stating which Strategy to Use for your current customer. In between page views…
  • 26. Challenge 3: How do we deal with all the data?
  • 27. Problem 1: Impossible fitting to all of the data in memory Move fully to “online” learning: Handle datapoint for datapoint Do not focus on ( theta | data ) but rather on ( theta | prior(s) ) • Summarize all meaningful info in the priors. Find out what data you need and don’t need to make an impact on the bottom line. • E.g. no demographic data Use M/R jobs for re-estimating
  • 28. Problem 2: Individual level estimates are needed fast Use hierarchical models: Aggregated level => Input for new users User level => Start model for known users Apply shrinkage Link the two levels Use user-level model in isolation if necessary Analytical updates thus very fast.
  • 29. Challenge 3: How do we deal with all the data: Use online learning and split different levels of the model
  • 30. Results Slide with the Increase inexample through: towell email click (at the 5th reminder) >100% Increase in e-commerce revenue: >25% 30 Beta Launch presentations Q2 2012 30
  • 31. My Big Data considerations: Focus on meaningful data: Persuasion at an individual level. Move from analytics to real time response: Provide real-time advice Inability to analyze all of the data: Use online learning and hierarchical models.
  • 32. End. Thanks! Contact us at: maurits@sciencerockstars.com +31 621262211 www.sciencerockstars.com

Editor's Notes

  1. What is big data?Hype, but we don’t really compyHowever, there are somethingschaning , because we have so much data…
  2. Briefly go through each of the six:Consensus (previous example)Liking (Similarity wallet example)Expertise (Milgram example)Commitment (Sign in garden example)Scarcity (Abundantly available example)Reciprocity (Free books example)
  3. They are already used online (Scarcity, Concensus, Scarcity)
  4. Talk through the two scenarios.
  5. So for each user its an estimate of what works. Which then can subsequently be used to select content.