Identifying Tourist Experiences in Maui, Hawaii Using Mobile Location Data

Abstract Spatial big data are revolutionizing the way that information is collected, stored and leveraged for decision-making. The advancements in spatial big data and their analytics have allowed for more granular-level information to be collected and analyzed on the spatiotemporal movements of people. However, critical reviews of spatial big data have found that many theoretical and quantitative misunderstandings exist which causes confusion for practitioners during applied practice. The level of information detail that can be confidently extracted from mobile data are not yet determined. In response, this paper strives to demonstrate the complexity of information that is available within mobile data through two inter-related objectives: (i) to explore the use of mobile data to group tourists based on their travel experience in Maui, Hawaii, and, (ii) to identify the linkage between accommodation types and travel experiences. Geofences were created around key points of interests and a k-means clustering was done in order to group travelers based on their travel experiences and time spent within these points of interest. It was found that tourist choices in accommodation resulted in distinct travel behaviors. This work provides a new use case of k-means clustering and mobile location data for the purpose of creating pseudo-loyalty data and consumer segments for points of interest that could not otherwise have data collected.