Recommendation of points of interest from user generated data collection

Systems that aim to predict user preferences and give recommendations are now commonly used in many systems such as online shops, social websites, and tourist guides. In this paper, we present a context aware personalized recommendation system on web and mobile, which recommends relevant location-based data from user collection and consisting of GPS routes and photos. We recommend three types of items: services, photos and GPS routes that are points of interests in user´s surrounding. We score all items from database based on four aspects of relevance: location, content, time and network. In order to personalize the results we built user profile based on user´s activity in the system. We study performance of the system within MOPSI.