2. Introduction
• Location-based Data Network (LBSN)
• Restaurants performance prediction
• Research Questions:
• Extract and combine different geographical or mobility features.
• Detect causal effects of location-based features on restaurant performance
2
3. Literature Review
• Restaurant performances prediction
• Location-based data usage
• Features extraction (2 types)
• Features combination (machine-learning-based techniques)
• Data source (Foursquare check-ins dataset)
3
6. Data
• Online reservation system
• Reservation availability information
• Restaurant specific information
• Location-based service & Social media
6
7. Challenges
• Choice of basic economic/behavior model
• Modification of the basic economic model (or feature combination)
• Classification for the purpose of causal effect examination
7
8. Potential Implication
• Help business managers decide a new location
• Help policy makers understand local economy
• Help location-based service to improve their performance
8
9. Reference
• [1] Anderson, Michael, and Jeremy Magruder. "Learning from the crowd: Regression discontinuity estimates
of the effects of an online review database*." The Economic Journal 122.563 (2012): 957-989.
• [2] Noulas, Anastasios, et al. "Mining user mobility features for next place prediction in location-based
services." Data Mining (ICDM), 2012 IEEE 12th International Conference on. IEEE, 2012.
• [3] Karamshuk, Dmytro, et al. "Geo-Spotting: Mining Online Location-based Services for Optimal Retail
Store Placement." arXiv preprint arXiv:1306.1704(2013).
• [4] Roick, Oliver, and Susanne Heuser. "Location Based Social Networks–Definition, Current State of the Art
and Research Agenda." Transactions in GIS(2013).
• [5] Noulas, Anastasios, et al. "An Empirical Study of Geographic User Activity Patterns in
Foursquare." ICWSM 11 (2011): 70-573.
9