Towards Mobile Intelligence: Learning From GPS History Data for Collaborative Recommendation
With the increasing popularity of location-based services, the authors have accumulated a lot of location data on the Web. In this paper, the authors are interested in answering two popular location-related queries in their daily life: if the people want to do something such as sightseeing or dining in a large city like Beijing, where should they go? If the people want to visit a place such as the Bird's Nest in Beijing Olympic park, what can they do there? They develop a mobile recommendation system to answer these queries. In the authors' system, they first model the users' location and activity histories as a user - location - activity rating tensor. Because each user has limited data, the resulting rating tensor is essentially very sparse.