BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Geo-Spotting: Mining Online Location-based Services for Optimal Re
 tail Store Placement - Dmytro Karamshuk (KCL)
DTSTART:20131016T120000Z
DTEND:20131016T130000Z
UID:TALK46894@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:The problem of identifying the optimal location for a new reta
 il store has been the focus of past research\, especially in the field of
  land economy\, due to its importance in the success of a business. Tradit
 ional approaches to the problem have factored in demographics\, revenue an
 d aggregated human flow statistics from nearby or remote areas. However\,
  the acquisition of relevant data is usually expensive. With the growth of
  location-based social networks\, fine grained data describing user mobil
 ity and popularity of places has recently become attainable.\n\nIn this pa
 per we study the predictive power of various machine learning features on 
 the popularity of retail stores in the city through the use of a dataset c
 ollected from Foursquare in New York. The features we mine are based on tw
 o general signals: geographic\, where features are formulated according to
  the types and density of nearby places\, and user mobility\, which includ
 es transitions between venues or the incoming flow of mobile users from d
 istant areas. Our evaluation suggests that the best performing features ar
 e common across the three different commercial chains considered in the an
 alysis\, although variations may exist too\, as explained by heterogeneiti
 es in the way retail facilities attract users. We also show that performan
 ce improves significantly when combining multiple features in supervised 
 learning algorithms\, suggesting that the retail success of a business may
  depend on multiple factors\n\nPaper: http://dl.acm.org/citation.cfm?id=24
 87616&CFID=356036745&CFTOKEN=23669279\n\nBio: Dmytro holds his PhD in comp
 uter science and engineering from IMT Lucca\, Italy in collaboration with 
 IIT CNR Pisa. This work was done while he was visiting Computer Lab\, Univ
 ersity of Cambridge in 2012. From August 2013 Dmytro is a postdoc at King
 ’s College London.\n
LOCATION:LT2\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR