Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement

Dima Karamshuk
Dima Karamshukdata scientist
Geo-Spotting: Mining Online Location-based
Services for Optimal Retail Store Placement
Dmytro Karamshuk
King's College London

Based on the paper:
D. Karamshuk, A. Noulas, S. Scellato, V. Nicosia, C. Mascolo. Geo-Spotting: Mining Online

Location-based Services for Optimal Retail Store Placement. ACM SIGKDD Conference on
Knowledge Discovery and Data Mining (KDD), Chicago, 2013
Optimal Retail Location Problem

Among L possible locations in the city select one where
a new store would be most profitable/popular.
Optimal Retail Location Problem
The problem is not new
●

A. Athiyaman. Location decision making: the case of retail service development in a
closed population. In Academy of Marketing Studies, volume 15, page 13, 2010.

●

O. Berman and D. Krass. The generalized maximal covering location problem.
Computers & Operations Research, 29(6):563–581, 2002.

●

A. Kubis and M. Hartmann. Analysis of location of large-area shopping centres. a
probabilistic gravity model for the halle-leipzig area. Jahrbuch für
Regionalwissenschaft, 27(1):43–57, 2007.

●

Pablo Jensen. Network-based predictions of retail store commercial categories and
optimal locations. Phys. Rev. E, 74:035101, Sep 2006.

Our approach:
explore fine-grained and cheap data from LBSN
Location-based social networks

●

check-in at places

●

share with your friends

●

receive bonuses for check-ins

●

search for places

●

leave comments for others
Check-ins around the world

over 40M users

over 4.5B check-ins
Collecting the Data

Dataset collected in New York
●

37K venues

●

47K users

●

621K checkins

●

May – November, 2010
accounts for »25% of the original data
How popular is a venue?

The distance between the two places is only few hundred meters
How popular is a venue?
Distribution of check-ins per place

Geographic distribution of venues

size = #checkin
●

popularity can be several orders of magnitude different from place to place

●

probably it depends on the location and types of places
Popularity and type of venue

●

different types and chains of
venues have different usage
patterns

●

we cannot compare check-ins
across venues of different
chains but we can across
individual chains

Number of check-ins per place for
individual chains of restaurants
Co-location with other venues
How frequently we observe a Starbucks close to a
railway station?

Does it influence the popularity of a restaurant?
Pablo Jensen. Analyzing the localization of retail stores
with complex systems tools. IDA ’09, pages 10–20, Berlin,
Heidelberg, 2009. Springer-Verlag.
User mobility between places
How many users go to a Starbucks
after railway station?

●

there is correspondence between colocation and mobility patterns

●

but also many discrepancies
Optimal Retail Location Problem

Among L possible locations in the city select one where new store would be most popular.
Define the area
An area is defined as a disc of radius r around a point with geographical coordinates l

The area is described by a set of numeric features
check-ins at venues in the disk.

designed from
Geographic features of an area
●

density – number of venues in the area

●

neighbors entropy – heterogeneity of venue types

●

competitiveness – percentage of competing venues
Geographic features of an area
●

quality by Jensen
–

define inter-types attractiveness coefficients

–

weight surrounding venues by their attractiveness
Mobility features of an area
●

area popularity – total number of checkins in the area

●

transition density – intensity of transitions inside the area

●

incoming flows – intensity of transitions from outside areas
Mobility features of an area
●

transition quality
●

define transition coefficients for each type

●

weight venues according to the product of coefficient and
check-ins volume
Ranking problem
Use area features

to rank all areas in a given set L

according to their potential popularity.

Compare with the ground truth: ranking of places basing
on their actual popularity.
Evaluation metrics
Compare the predicted and ground truth rankings.
●

Top-K locations ranking – use NDCG@K

●

Accuracy of the best prediction – Accuracy@X% of having the
best predicted store in the Top-X% of ground truth ranking
We explore random cross-validation approach and report
average values across all experiments.
Performance of individual features
NDCG@10

●

some indicators are general across various chains while some are chain-specific

●

the lack of competitors in the area play positive role as do the existence of place attractors

●

performance of In.Flow is in accordance with the fact that McDonalds attract more users
from the remote areas
Considering fusion of factors
Explore the fusion of features in a supervised learning approach

●

regression for ranking – conduct regression using Linear Regression,
SVR or M5P and then rank according to regressed values

●

pair-wise ranking – learn on pair-wise comparison using neural
networks RankNet

Use the same evaluation methodology as for individual features.
Results of the supervised learning
NDCG@10

Individual features

Supervised learning

●

supervised learning has better performance than the the best individual feature

●

the combination of geographic features and mobility features yields better result than
the combination of geographic features alone

●

regression to rank with SVR is the best performing technique
The best location prediction

Supervised learning
Individual features
●

supervised learning yields reliable and significantly improved result

●

the best prediction lies in top-20% of the ground truth ranking with
probability over 80%
Implications
●

we show how fine-grained data from location-based social networks
can be effectively explored in geographic retail analysis

●

this can inspire further works in location-based advertising, developing
indexes of urban areas, provision of location-based services etc. etc.

●

particularly we see a lot of potential in the approach of measuring user
flows from check-ins in various applications

●

we also faced some challenges when scaling this approach to other
chains and cities
Thank you for your attention!
Dmytro Karamshuk
King's College London
follow me on Twitter: @karamshuk
1 of 25

Recommended

Site suitability analysis for constructing New ATM in Margao , Goa by
Site suitability analysis for constructing New ATM in Margao , GoaSite suitability analysis for constructing New ATM in Margao , Goa
Site suitability analysis for constructing New ATM in Margao , Goasuyog patwardhan
1.9K views30 slides
datavis samples by
datavis samplesdatavis samples
datavis samplesChloe Ng
88 views33 slides
Airline analytics for the 21st century by
Airline analytics for the 21st centuryAirline analytics for the 21st century
Airline analytics for the 21st centuryFaical Allou
2.8K views13 slides
How technology influences airline planning by
How technology influences airline planningHow technology influences airline planning
How technology influences airline planningFaical Allou
2.3K views15 slides
Revisiting the Generality of the Rank-based Human Mobility Model by
Revisiting the Generality of the Rank-based Human Mobility ModelRevisiting the Generality of the Rank-based Human Mobility Model
Revisiting the Generality of the Rank-based Human Mobility ModelDarshan Santani
771 views22 slides
Modeling Human Mobility by
Modeling Human Mobility Modeling Human Mobility
Modeling Human Mobility Dima Karamshuk
4.9K views32 slides

More Related Content

Viewers also liked

Locations and Networks at scale: From insights to predictive models, workshop... by
Locations and Networks at scale: From insights to predictive models, workshop...Locations and Networks at scale: From insights to predictive models, workshop...
Locations and Networks at scale: From insights to predictive models, workshop...Dima Karamshuk
627 views7 slides
Identifying Partisan Slant in News Articles and Twitter during Political Crises by
Identifying Partisan Slant in News Articles and Twitter during Political CrisesIdentifying Partisan Slant in News Articles and Twitter during Political Crises
Identifying Partisan Slant in News Articles and Twitter during Political CrisesDima Karamshuk
993 views12 slides
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB... by
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...Dima Karamshuk
3K views26 slides
CD-GAIN: Content Delivery Through the Analysis of Users' Access Patterns, ta... by
CD-GAIN: Content Delivery  Through the Analysis of Users' Access Patterns, ta...CD-GAIN: Content Delivery  Through the Analysis of Users' Access Patterns, ta...
CD-GAIN: Content Delivery Through the Analysis of Users' Access Patterns, ta...Dima Karamshuk
1.1K views25 slides
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser... by
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...Dima Karamshuk
948 views17 slides
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser... by
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...Dima Karamshuk
919 views19 slides

Viewers also liked(11)

Locations and Networks at scale: From insights to predictive models, workshop... by Dima Karamshuk
Locations and Networks at scale: From insights to predictive models, workshop...Locations and Networks at scale: From insights to predictive models, workshop...
Locations and Networks at scale: From insights to predictive models, workshop...
Dima Karamshuk627 views
Identifying Partisan Slant in News Articles and Twitter during Political Crises by Dima Karamshuk
Identifying Partisan Slant in News Articles and Twitter during Political CrisesIdentifying Partisan Slant in News Articles and Twitter during Political Crises
Identifying Partisan Slant in News Articles and Twitter during Political Crises
Dima Karamshuk993 views
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB... by Dima Karamshuk
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...
ISP-friendly Peer-assisted On-demand Streaming of Long Duration Content in BB...
Dima Karamshuk3K views
CD-GAIN: Content Delivery Through the Analysis of Users' Access Patterns, ta... by Dima Karamshuk
CD-GAIN: Content Delivery  Through the Analysis of Users' Access Patterns, ta...CD-GAIN: Content Delivery  Through the Analysis of Users' Access Patterns, ta...
CD-GAIN: Content Delivery Through the Analysis of Users' Access Patterns, ta...
Dima Karamshuk1.1K views
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser... by Dima Karamshuk
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
Dima Karamshuk948 views
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser... by Dima Karamshuk
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
On Factors Affecting the Usage and Adoption of a Nation-wide TV Streaming Ser...
Dima Karamshuk919 views
Modeling the Social, Spatial, and Temporal dimensions of Human Mobility in a ... by Dima Karamshuk
Modeling the Social, Spatial, and Temporal dimensions of Human Mobility in a ...Modeling the Social, Spatial, and Temporal dimensions of Human Mobility in a ...
Modeling the Social, Spatial, and Temporal dimensions of Human Mobility in a ...
Dima Karamshuk6.7K views
Take-away TV: Recharging Work Commutes with Greedy and Predictive Preloading ... by Dima Karamshuk
Take-away TV: Recharging Work Commutes with Greedy and Predictive Preloading ...Take-away TV: Recharging Work Commutes with Greedy and Predictive Preloading ...
Take-away TV: Recharging Work Commutes with Greedy and Predictive Preloading ...
Dima Karamshuk703 views
GEOVISUALIZING SPATIO-TEMPORAL PATTERNS IN TENNIS by Damien Demaj
GEOVISUALIZING SPATIO-TEMPORAL PATTERNS IN TENNISGEOVISUALIZING SPATIO-TEMPORAL PATTERNS IN TENNIS
GEOVISUALIZING SPATIO-TEMPORAL PATTERNS IN TENNIS
Damien Demaj7.3K views
Human mobility,urban structure analysis,and spatial community detection from ... by Song Gao
Human mobility,urban structure analysis,and spatial community detection from ...Human mobility,urban structure analysis,and spatial community detection from ...
Human mobility,urban structure analysis,and spatial community detection from ...
Song Gao3.2K views
AgensGraph: a Multi-model Graph Database based on PostgreSql by Kisung Kim
AgensGraph: a Multi-model Graph Database based on PostgreSqlAgensGraph: a Multi-model Graph Database based on PostgreSql
AgensGraph: a Multi-model Graph Database based on PostgreSql
Kisung Kim4.3K views

Similar to Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement

Introduction to Targomo by
Introduction to TargomoIntroduction to Targomo
Introduction to TargomoTargomo GmbH
61 views18 slides
A Big Data Telco Solution by Dr. Laura Wynter by
A Big Data Telco Solution by Dr. Laura WynterA Big Data Telco Solution by Dr. Laura Wynter
A Big Data Telco Solution by Dr. Laura Wynterwkwsci-research
4.1K views34 slides
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016 by
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016MLconf
928 views28 slides
I ii x_slides_albakour_online by
I ii x_slides_albakour_onlineI ii x_slides_albakour_online
I ii x_slides_albakour_onlineDyaa AlBakour
990 views26 slides
GIS by
GISGIS
GISNirajChaudhari23
22 views13 slides
Volunteering assistance to online geocoding services through a distributed kn... by
Volunteering assistance to online geocoding services through a distributed kn...Volunteering assistance to online geocoding services through a distributed kn...
Volunteering assistance to online geocoding services through a distributed kn...José Pablo Gómez Barrón S.
521 views19 slides

Similar to Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement(20)

Introduction to Targomo by Targomo GmbH
Introduction to TargomoIntroduction to Targomo
Introduction to Targomo
Targomo GmbH61 views
A Big Data Telco Solution by Dr. Laura Wynter by wkwsci-research
A Big Data Telco Solution by Dr. Laura WynterA Big Data Telco Solution by Dr. Laura Wynter
A Big Data Telco Solution by Dr. Laura Wynter
wkwsci-research4.1K views
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016 by MLconf
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016
Jonathan Lenaghan, VP of Science and Technology, PlaceIQ at MLconf ATL 2016
MLconf928 views
I ii x_slides_albakour_online by Dyaa AlBakour
I ii x_slides_albakour_onlineI ii x_slides_albakour_online
I ii x_slides_albakour_online
Dyaa AlBakour990 views
Multidimensional scaling & Conjoint Analysis by Omer Maroof
Multidimensional scaling & Conjoint AnalysisMultidimensional scaling & Conjoint Analysis
Multidimensional scaling & Conjoint Analysis
Omer Maroof10.9K views
Using Spatial Analysis to Drive Post-Pandemic Site Selection in Retail by CARTO
Using Spatial Analysis to Drive Post-Pandemic Site Selection in RetailUsing Spatial Analysis to Drive Post-Pandemic Site Selection in Retail
Using Spatial Analysis to Drive Post-Pandemic Site Selection in Retail
CARTO282 views
Improving the Mobile Customer Experience by Combining User Behaviour Analysis... by Merlien Institute
Improving the Mobile Customer Experience by Combining User Behaviour Analysis...Improving the Mobile Customer Experience by Combining User Behaviour Analysis...
Improving the Mobile Customer Experience by Combining User Behaviour Analysis...
Merlien Institute636 views
Location, mobile,geofences, proximity targeting, ,location, audience targetin... by Mike Maiorano
Location, mobile,geofences, proximity targeting, ,location, audience targetin...Location, mobile,geofences, proximity targeting, ,location, audience targetin...
Location, mobile,geofences, proximity targeting, ,location, audience targetin...
Mike Maiorano729 views
Maximizing Benefits via a Scoring Framework for Location-Based Services by Cognizant
Maximizing Benefits via a Scoring Framework for Location-Based ServicesMaximizing Benefits via a Scoring Framework for Location-Based Services
Maximizing Benefits via a Scoring Framework for Location-Based Services
Cognizant1.6K views
Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerce by Ladislav Peska
Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerceOff-line vs. On-line Evaluation of Recommender Systems in Small E-commerce
Off-line vs. On-line Evaluation of Recommender Systems in Small E-commerce
Ladislav Peska229 views
Applications Of GIS In Business Decision Making The Case Of Egypt by Leslie Schulte
Applications Of GIS In Business Decision Making  The Case Of EgyptApplications Of GIS In Business Decision Making  The Case Of Egypt
Applications Of GIS In Business Decision Making The Case Of Egypt
Leslie Schulte4 views
Orchestrating Collective Intelligence by Turi, Inc.
Orchestrating Collective IntelligenceOrchestrating Collective Intelligence
Orchestrating Collective Intelligence
Turi, Inc.350 views
Csr about by CSR
Csr aboutCsr about
Csr about
CSR 1.5K views
New Research Articles 2020 November Issue International Journal of Software E... by ijseajournal
New Research Articles 2020 November Issue International Journal of Software E...New Research Articles 2020 November Issue International Journal of Software E...
New Research Articles 2020 November Issue International Journal of Software E...
ijseajournal9 views
Geo-Enablement of the Supply Chain Analytics by Nishant Sinha
Geo-Enablement of the Supply Chain AnalyticsGeo-Enablement of the Supply Chain Analytics
Geo-Enablement of the Supply Chain Analytics
Nishant Sinha449 views

Recently uploaded

Future of AR - Facebook Presentation by
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook PresentationRob McCarty
65 views27 slides
AI + Memoori = AIM by
AI + Memoori = AIMAI + Memoori = AIM
AI + Memoori = AIMMemoori
14 views9 slides
Inawisdom IDP by
Inawisdom IDPInawisdom IDP
Inawisdom IDPPhilipBasford
15 views48 slides
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdf by
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdfAdopting Karpenter for Cost and Simplicity at Grafana Labs.pdf
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdfMichaelOLeary82
13 views74 slides
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdf by
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdfBronack Skills - Risk Management and SRE v1.0 12-3-2023.pdf
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdfThomasBronack
31 views31 slides
AIM102-S_Cognizant_CognizantCognitive by
AIM102-S_Cognizant_CognizantCognitiveAIM102-S_Cognizant_CognizantCognitive
AIM102-S_Cognizant_CognizantCognitivePhilipBasford
21 views36 slides

Recently uploaded(20)

Future of AR - Facebook Presentation by Rob McCarty
Future of AR - Facebook PresentationFuture of AR - Facebook Presentation
Future of AR - Facebook Presentation
Rob McCarty65 views
AI + Memoori = AIM by Memoori
AI + Memoori = AIMAI + Memoori = AIM
AI + Memoori = AIM
Memoori14 views
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdf by MichaelOLeary82
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdfAdopting Karpenter for Cost and Simplicity at Grafana Labs.pdf
Adopting Karpenter for Cost and Simplicity at Grafana Labs.pdf
MichaelOLeary8213 views
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdf by ThomasBronack
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdfBronack Skills - Risk Management and SRE v1.0 12-3-2023.pdf
Bronack Skills - Risk Management and SRE v1.0 12-3-2023.pdf
ThomasBronack31 views
AIM102-S_Cognizant_CognizantCognitive by PhilipBasford
AIM102-S_Cognizant_CognizantCognitiveAIM102-S_Cognizant_CognizantCognitive
AIM102-S_Cognizant_CognizantCognitive
PhilipBasford21 views
The Power of Generative AI in Accelerating No Code Adoption.pdf by Saeed Al Dhaheri
The Power of Generative AI in Accelerating No Code Adoption.pdfThe Power of Generative AI in Accelerating No Code Adoption.pdf
The Power of Generative AI in Accelerating No Code Adoption.pdf
Saeed Al Dhaheri39 views
Initiating and Advancing Your Strategic GIS Governance Strategy by Safe Software
Initiating and Advancing Your Strategic GIS Governance StrategyInitiating and Advancing Your Strategic GIS Governance Strategy
Initiating and Advancing Your Strategic GIS Governance Strategy
Safe Software184 views
GDSC GLAU Info Session.pptx by gauriverrma4
GDSC GLAU Info Session.pptxGDSC GLAU Info Session.pptx
GDSC GLAU Info Session.pptx
gauriverrma415 views
The Power of Heat Decarbonisation Plans in the Built Environment by IES VE
The Power of Heat Decarbonisation Plans in the Built EnvironmentThe Power of Heat Decarbonisation Plans in the Built Environment
The Power of Heat Decarbonisation Plans in the Built Environment
IES VE84 views
The Role of Patterns in the Era of Large Language Models by Yunyao Li
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language Models
Yunyao Li91 views
Business Analyst Series 2023 - Week 4 Session 7 by DianaGray10
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7
DianaGray10146 views
Deep Tech and the Amplified Organisation: Core Concepts by Holonomics
Deep Tech and the Amplified Organisation: Core ConceptsDeep Tech and the Amplified Organisation: Core Concepts
Deep Tech and the Amplified Organisation: Core Concepts
Holonomics17 views
Optimizing Communication to Optimize Human Behavior - LCBM by Yaman Kumar
Optimizing Communication to Optimize Human Behavior - LCBMOptimizing Communication to Optimize Human Behavior - LCBM
Optimizing Communication to Optimize Human Behavior - LCBM
Yaman Kumar38 views
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023 by BookNet Canada
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023Redefining the book supply chain: A glimpse into the future - Tech Forum 2023
Redefining the book supply chain: A glimpse into the future - Tech Forum 2023
BookNet Canada44 views
"Package management in monorepos", Zoltan Kochan by Fwdays
"Package management in monorepos", Zoltan Kochan"Package management in monorepos", Zoltan Kochan
"Package management in monorepos", Zoltan Kochan
Fwdays34 views
"Node.js Development in 2024: trends and tools", Nikita Galkin by Fwdays
"Node.js Development in 2024: trends and tools", Nikita Galkin "Node.js Development in 2024: trends and tools", Nikita Galkin
"Node.js Development in 2024: trends and tools", Nikita Galkin
Fwdays33 views
Transcript: Redefining the book supply chain: A glimpse into the future - Tec... by BookNet Canada
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
Transcript: Redefining the book supply chain: A glimpse into the future - Tec...
BookNet Canada41 views
NTGapps NTG LowCode Platform by Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu437 views

Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement

  • 1. Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement Dmytro Karamshuk King's College London Based on the paper: D. Karamshuk, A. Noulas, S. Scellato, V. Nicosia, C. Mascolo. Geo-Spotting: Mining Online Location-based Services for Optimal Retail Store Placement. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Chicago, 2013
  • 2. Optimal Retail Location Problem Among L possible locations in the city select one where a new store would be most profitable/popular.
  • 3. Optimal Retail Location Problem The problem is not new ● A. Athiyaman. Location decision making: the case of retail service development in a closed population. In Academy of Marketing Studies, volume 15, page 13, 2010. ● O. Berman and D. Krass. The generalized maximal covering location problem. Computers & Operations Research, 29(6):563–581, 2002. ● A. Kubis and M. Hartmann. Analysis of location of large-area shopping centres. a probabilistic gravity model for the halle-leipzig area. Jahrbuch für Regionalwissenschaft, 27(1):43–57, 2007. ● Pablo Jensen. Network-based predictions of retail store commercial categories and optimal locations. Phys. Rev. E, 74:035101, Sep 2006. Our approach: explore fine-grained and cheap data from LBSN
  • 4. Location-based social networks ● check-in at places ● share with your friends ● receive bonuses for check-ins ● search for places ● leave comments for others
  • 5. Check-ins around the world over 40M users over 4.5B check-ins
  • 6. Collecting the Data Dataset collected in New York ● 37K venues ● 47K users ● 621K checkins ● May – November, 2010 accounts for »25% of the original data
  • 7. How popular is a venue? The distance between the two places is only few hundred meters
  • 8. How popular is a venue? Distribution of check-ins per place Geographic distribution of venues size = #checkin ● popularity can be several orders of magnitude different from place to place ● probably it depends on the location and types of places
  • 9. Popularity and type of venue ● different types and chains of venues have different usage patterns ● we cannot compare check-ins across venues of different chains but we can across individual chains Number of check-ins per place for individual chains of restaurants
  • 10. Co-location with other venues How frequently we observe a Starbucks close to a railway station? Does it influence the popularity of a restaurant? Pablo Jensen. Analyzing the localization of retail stores with complex systems tools. IDA ’09, pages 10–20, Berlin, Heidelberg, 2009. Springer-Verlag.
  • 11. User mobility between places How many users go to a Starbucks after railway station? ● there is correspondence between colocation and mobility patterns ● but also many discrepancies
  • 12. Optimal Retail Location Problem Among L possible locations in the city select one where new store would be most popular.
  • 13. Define the area An area is defined as a disc of radius r around a point with geographical coordinates l The area is described by a set of numeric features check-ins at venues in the disk. designed from
  • 14. Geographic features of an area ● density – number of venues in the area ● neighbors entropy – heterogeneity of venue types ● competitiveness – percentage of competing venues
  • 15. Geographic features of an area ● quality by Jensen – define inter-types attractiveness coefficients – weight surrounding venues by their attractiveness
  • 16. Mobility features of an area ● area popularity – total number of checkins in the area ● transition density – intensity of transitions inside the area ● incoming flows – intensity of transitions from outside areas
  • 17. Mobility features of an area ● transition quality ● define transition coefficients for each type ● weight venues according to the product of coefficient and check-ins volume
  • 18. Ranking problem Use area features to rank all areas in a given set L according to their potential popularity. Compare with the ground truth: ranking of places basing on their actual popularity.
  • 19. Evaluation metrics Compare the predicted and ground truth rankings. ● Top-K locations ranking – use NDCG@K ● Accuracy of the best prediction – Accuracy@X% of having the best predicted store in the Top-X% of ground truth ranking We explore random cross-validation approach and report average values across all experiments.
  • 20. Performance of individual features NDCG@10 ● some indicators are general across various chains while some are chain-specific ● the lack of competitors in the area play positive role as do the existence of place attractors ● performance of In.Flow is in accordance with the fact that McDonalds attract more users from the remote areas
  • 21. Considering fusion of factors Explore the fusion of features in a supervised learning approach ● regression for ranking – conduct regression using Linear Regression, SVR or M5P and then rank according to regressed values ● pair-wise ranking – learn on pair-wise comparison using neural networks RankNet Use the same evaluation methodology as for individual features.
  • 22. Results of the supervised learning NDCG@10 Individual features Supervised learning ● supervised learning has better performance than the the best individual feature ● the combination of geographic features and mobility features yields better result than the combination of geographic features alone ● regression to rank with SVR is the best performing technique
  • 23. The best location prediction Supervised learning Individual features ● supervised learning yields reliable and significantly improved result ● the best prediction lies in top-20% of the ground truth ranking with probability over 80%
  • 24. Implications ● we show how fine-grained data from location-based social networks can be effectively explored in geographic retail analysis ● this can inspire further works in location-based advertising, developing indexes of urban areas, provision of location-based services etc. etc. ● particularly we see a lot of potential in the approach of measuring user flows from check-ins in various applications ● we also faced some challenges when scaling this approach to other chains and cities
  • 25. Thank you for your attention! Dmytro Karamshuk King's College London follow me on Twitter: @karamshuk