BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Where Can I Buy a Boulder? Searching for Offline Retail Locations 
 - Sandro Bauer (University of Cambridge)
DTSTART:20160408T110000Z
DTEND:20160408T120000Z
UID:TALK65529@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:People commonly need to purchase things in person\, from large
  garden supplies to home decor. Although modern search systems are very ef
 fective at finding online products\, little research attention has been\np
 aid to helping users find places that sell a specific product offline. For
  instance\, users searching for an apron are not typically directed to a n
 earby kitchen store by a standard search engine. In this paper\, we invest
 igate “where can I buy”-style queries related to in-person purchases o
 f products and services. Answering these queries is challenging since litt
 le is known about the range of products sold in many stores\, especially t
 hose which are smaller in size. To better understand this class of queries
 \, we first present an in-depth analysis of typical offline purchase needs
  as observed by a major search engine\, producing an ontology of such need
 s. We then propose ranking features\nfor this new problem\, and learn a ra
 nking function that returns stores most likely to sell a queried item or s
 ervice\, even if there is very little information available online about s
 ome of the stores. Our final\ncontribution is a new evaluation framework t
 hat combines distance with store relevance in measuring the effectiveness 
 of such a search system. We evaluate our method using this approach and sh
 ow that it outperforms\na modern web search engine.\n\nThis work was done 
 jointly with Filip Radlinski and Ryen White during an internship at Micros
 oft Research.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR