Improving Destination Choice Modeling Using Location-Based Big Data

Citizens are increasingly sharing their location and movements through‘check-ins’ on location based social networks (LBSNs). These services are collecting unprecedented amounts of big data that can be used to study how we travel and interact with our environment. This paper will present the development of a destination choice model for Ontario, Canada which uses data from Foursquare, the largest LBSN to model destination attractiveness. Models are estimated for leisure, visit and business long distance travel purposes separately. A methodology to collect, process and aggregate historical check-in counts has been developed, allowing the utility of each destination to be calculated based on the intensity of different activities performed at the destination. Destinations such as national parks and ski areas are very strong attractors of leisure trips, yet do not employ many people, and have few residents. Trip counts to such destinations are therefore poorly predicted by models based on population and employment. Traditionally, this has been remedied by extensive manual data collection. The integration of Foursquare data offers an alternative approach to solve this problem that has not been deeply explored until now.The Foursquare based destination choice model is evaluated against a traditional model that is estimated only with population and employment. The results demonstrate that data from LBSNs can be used to improve destination choice models, particularly for leisure travel.