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 ● 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. The problem is not new 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? ● popularity can be several orders of magnitude different from place to place Distribution of check-ins per place Geographic distribution of venues size = #checkin ● 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 co- location 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 designed from check-ins at venues in the disk. 

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 ● 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 NDCG@10 

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 ● 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 NDCG@10 Individual features Supervised learning 

The best location prediction ● supervised learning yields reliable and significantly improved result ● the best prediction lies in top-20% of the ground truth ranking with probability over 80% Individual features Supervised learning 

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