SlideShare a Scribd company logo
Ads and the City:
Considering Geographic Distance Goes a
              Long Way

 Diego Saez-Trumper1         Daniele Quercia 2           Jon Crowcroft 2

                  1
                    Universitat Pompeu Fabra, Barcelona
            2
                Computer Laboratory, University of Cambridge


                      Dublin, September, 2012
mobile social-networking sites
Category        #Venues    #Users
        food          1,293      1,566
      nightlife       1,075      1,207
       travel          850       1,744
  home/work/etc.       411       1,037
       shops           362        878
arts&entertainment     348        841
  parks&outdoors       184        363
     education         49         117
        Total         4,572      3,110
     Table: London Foursquare Data
Given a venue, suggests guests
Context




similar to target advertising (?)
domain knowledge in people mobility
On people mobility (from the literature)




distance matters
likes might matter
“power users” are special
             p(go|like, close) ∝ pgo · pclose · plike
plike




                         #venues visited by user u with rating lui
   p(like = lui |go) =
                             total #venues visited by user u

lui is ranking obtained from item-based CF algorithm.
pgo




        #venues visited by user u
pgo =
             total #venues
pclose


               1
pclose = k1     α
              dui
pclose


               1
pclose = k1     α
              dui
pclose


                           1
            pclose = k1     α
                          dui


           Category                α
              food                1.64
            nightlife             1.61
travel (airports/trainstations)   2.22
       home/work/etc.             1.62
             shops                1.64
     arts&entertainment           1.64
       parks&outdoors             1.68
           education              1.93

      High α → travel farther
p(go|like, close) ∝ pgo · pclose · plike


Naive Bayesian
Bayesian
Linear Regression
Results
Results
Results
Results


           1.0



                                                                                           p_go
                                                                                           p_close
                                                                                           p_like
           0.8




                                                                                           Naive
                                                                                           Bayesian
                                                                                           Linear Reg.
           0.6
accuracy

           0.4
           0.2
           0.0




                 Arts.and.Ent.   Education   Food   HomeWork   Nightlife   Parks   Shops   Travel
Discussion




scalability
cold start situation
When it does not work
When It Does not Work
When It Does not Work
Final Remarks




results depend on venue category (different α and predictability)
geographic closeness plays a very important role.
domain knowledge significantly improves recommendations
results.
“Understanding the specifics of your domain
 is critical to building a good recommender”


         Paul Lamere @ recsys’12
Questions?

More Related Content

More from Daniele Quercia

The Digital Life of Walkable Streets
The Digital Life of Walkable StreetsThe Digital Life of Walkable Streets
The Digital Life of Walkable Streets
Daniele Quercia
 
Psychological Maps 2.0 [www 2013]
Psychological Maps 2.0 [www 2013]Psychological Maps 2.0 [www 2013]
Psychological Maps 2.0 [www 2013]Daniele Quercia
 
Urban*: Crowdsourcing for the Good of London
Urban*: Crowdsourcing for the Good of LondonUrban*: Crowdsourcing for the Good of London
Urban*: Crowdsourcing for the Good of London
Daniele Quercia
 
Trend Makers and Trend Spotters in a Mobile Application
Trend Makers and Trend Spotters in a Mobile ApplicationTrend Makers and Trend Spotters in a Mobile Application
Trend Makers and Trend Spotters in a Mobile Application
Daniele Quercia
 
Finger on the Pulse: Towards a Real-time City Health Monitor
Finger on the Pulse: Towards a Real-time City Health MonitorFinger on the Pulse: Towards a Real-time City Health Monitor
Finger on the Pulse: Towards a Real-time City Health MonitorDaniele Quercia
 
Spotting Trends: The Wisdom of the Few
Spotting Trends: The Wisdom of the FewSpotting Trends: The Wisdom of the Few
Spotting Trends: The Wisdom of the Few
Daniele Quercia
 
Unleashing the potential of spatial data
Unleashing the potential of spatial dataUnleashing the potential of spatial data
Unleashing the potential of spatial data
Daniele Quercia
 
Loosing "Friends" on Facebook
Loosing "Friends" on FacebookLoosing "Friends" on Facebook
Loosing "Friends" on Facebook
Daniele Quercia
 
Talk of the City: Londoners and Social Media
Talk of the City: Londoners and Social MediaTalk of the City: Londoners and Social Media
Talk of the City: Londoners and Social Media
Daniele Quercia
 
The Social World of Twitter: Topics, Geography, and Emotions
The Social World of Twitter: Topics, Geography, and EmotionsThe Social World of Twitter: Topics, Geography, and Emotions
The Social World of Twitter: Topics, Geography, and Emotions
Daniele Quercia
 
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
Daniele Quercia
 
Middleware for social computing: a roadmap
Middleware for social computing: a roadmap	Middleware for social computing: a roadmap
Middleware for social computing: a roadmap
Daniele Quercia
 
Auralist: Introducing Serendipity into Music Recommendation
Auralist: Introducing Serendipity into Music RecommendationAuralist: Introducing Serendipity into Music Recommendation
Auralist: Introducing Serendipity into Music Recommendation
Daniele Quercia
 
Personality in Twitter: influentials and popular users
Personality in Twitter: influentials and popular usersPersonality in Twitter: influentials and popular users
Personality in Twitter: influentials and popular usersDaniele Quercia
 
In the mood for being influential
In the mood for being influential In the mood for being influential
In the mood for being influential
Daniele Quercia
 
Geomob London September 2011
Geomob London September 2011Geomob London September 2011
Geomob London September 2011Daniele Quercia
 
Rethinking Mobile Recommendations
Rethinking Mobile RecommendationsRethinking Mobile Recommendations
Rethinking Mobile Recommendations
Daniele Quercia
 
FriendSensing
FriendSensingFriendSensing
FriendSensing
Daniele Quercia
 
Sybil Attacks Against Mobile Users
Sybil Attacks Against Mobile UsersSybil Attacks Against Mobile Users
Sybil Attacks Against Mobile Users
Daniele Quercia
 
Promoting location privacy… one lie at a time
Promoting location privacy… one lie at a timePromoting location privacy… one lie at a time
Promoting location privacy… one lie at a time
Daniele Quercia
 

More from Daniele Quercia (20)

The Digital Life of Walkable Streets
The Digital Life of Walkable StreetsThe Digital Life of Walkable Streets
The Digital Life of Walkable Streets
 
Psychological Maps 2.0 [www 2013]
Psychological Maps 2.0 [www 2013]Psychological Maps 2.0 [www 2013]
Psychological Maps 2.0 [www 2013]
 
Urban*: Crowdsourcing for the Good of London
Urban*: Crowdsourcing for the Good of LondonUrban*: Crowdsourcing for the Good of London
Urban*: Crowdsourcing for the Good of London
 
Trend Makers and Trend Spotters in a Mobile Application
Trend Makers and Trend Spotters in a Mobile ApplicationTrend Makers and Trend Spotters in a Mobile Application
Trend Makers and Trend Spotters in a Mobile Application
 
Finger on the Pulse: Towards a Real-time City Health Monitor
Finger on the Pulse: Towards a Real-time City Health MonitorFinger on the Pulse: Towards a Real-time City Health Monitor
Finger on the Pulse: Towards a Real-time City Health Monitor
 
Spotting Trends: The Wisdom of the Few
Spotting Trends: The Wisdom of the FewSpotting Trends: The Wisdom of the Few
Spotting Trends: The Wisdom of the Few
 
Unleashing the potential of spatial data
Unleashing the potential of spatial dataUnleashing the potential of spatial data
Unleashing the potential of spatial data
 
Loosing "Friends" on Facebook
Loosing "Friends" on FacebookLoosing "Friends" on Facebook
Loosing "Friends" on Facebook
 
Talk of the City: Londoners and Social Media
Talk of the City: Londoners and Social MediaTalk of the City: Londoners and Social Media
Talk of the City: Londoners and Social Media
 
The Social World of Twitter: Topics, Geography, and Emotions
The Social World of Twitter: Topics, Geography, and EmotionsThe Social World of Twitter: Topics, Geography, and Emotions
The Social World of Twitter: Topics, Geography, and Emotions
 
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
Facebook and Privacy: The Balancing Act of Personality, Gender, and Relations...
 
Middleware for social computing: a roadmap
Middleware for social computing: a roadmap	Middleware for social computing: a roadmap
Middleware for social computing: a roadmap
 
Auralist: Introducing Serendipity into Music Recommendation
Auralist: Introducing Serendipity into Music RecommendationAuralist: Introducing Serendipity into Music Recommendation
Auralist: Introducing Serendipity into Music Recommendation
 
Personality in Twitter: influentials and popular users
Personality in Twitter: influentials and popular usersPersonality in Twitter: influentials and popular users
Personality in Twitter: influentials and popular users
 
In the mood for being influential
In the mood for being influential In the mood for being influential
In the mood for being influential
 
Geomob London September 2011
Geomob London September 2011Geomob London September 2011
Geomob London September 2011
 
Rethinking Mobile Recommendations
Rethinking Mobile RecommendationsRethinking Mobile Recommendations
Rethinking Mobile Recommendations
 
FriendSensing
FriendSensingFriendSensing
FriendSensing
 
Sybil Attacks Against Mobile Users
Sybil Attacks Against Mobile UsersSybil Attacks Against Mobile Users
Sybil Attacks Against Mobile Users
 
Promoting location privacy… one lie at a time
Promoting location privacy… one lie at a timePromoting location privacy… one lie at a time
Promoting location privacy… one lie at a time
 

Recently uploaded

Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Thierry Lestable
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
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
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Product School
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
Product School
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
Elena Simperl
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
RTTS
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 

Recently uploaded (20)

Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
Empowering NextGen Mobility via Large Action Model Infrastructure (LAMI): pav...
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
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
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...Mission to Decommission: Importance of Decommissioning Products to Increase E...
Mission to Decommission: Importance of Decommissioning Products to Increase E...
 
How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...How world-class product teams are winning in the AI era by CEO and Founder, P...
How world-class product teams are winning in the AI era by CEO and Founder, P...
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Knowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and backKnowledge engineering: from people to machines and back
Knowledge engineering: from people to machines and back
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
JMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and GrafanaJMeter webinar - integration with InfluxDB and Grafana
JMeter webinar - integration with InfluxDB and Grafana
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 

Ads and the City

  • 1. Ads and the City: Considering Geographic Distance Goes a Long Way Diego Saez-Trumper1 Daniele Quercia 2 Jon Crowcroft 2 1 Universitat Pompeu Fabra, Barcelona 2 Computer Laboratory, University of Cambridge Dublin, September, 2012
  • 3. Category #Venues #Users food 1,293 1,566 nightlife 1,075 1,207 travel 850 1,744 home/work/etc. 411 1,037 shops 362 878 arts&entertainment 348 841 parks&outdoors 184 363 education 49 117 Total 4,572 3,110 Table: London Foursquare Data
  • 4. Given a venue, suggests guests
  • 5. Context similar to target advertising (?) domain knowledge in people mobility
  • 6. On people mobility (from the literature) distance matters likes might matter “power users” are special p(go|like, close) ∝ pgo · pclose · plike
  • 7. plike #venues visited by user u with rating lui p(like = lui |go) = total #venues visited by user u lui is ranking obtained from item-based CF algorithm.
  • 8. pgo #venues visited by user u pgo = total #venues
  • 9. pclose 1 pclose = k1 α dui
  • 10. pclose 1 pclose = k1 α dui
  • 11. pclose 1 pclose = k1 α dui Category α food 1.64 nightlife 1.61 travel (airports/trainstations) 2.22 home/work/etc. 1.62 shops 1.64 arts&entertainment 1.64 parks&outdoors 1.68 education 1.93 High α → travel farther
  • 12. p(go|like, close) ∝ pgo · pclose · plike Naive Bayesian Bayesian Linear Regression
  • 16. Results 1.0 p_go p_close p_like 0.8 Naive Bayesian Linear Reg. 0.6 accuracy 0.4 0.2 0.0 Arts.and.Ent. Education Food HomeWork Nightlife Parks Shops Travel
  • 18. When it does not work
  • 19. When It Does not Work
  • 20. When It Does not Work
  • 21. Final Remarks results depend on venue category (different α and predictability) geographic closeness plays a very important role. domain knowledge significantly improves recommendations results.
  • 22. “Understanding the specifics of your domain is critical to building a good recommender” Paul Lamere @ recsys’12