Successive Point-of-Interest Recommendation with Local Differential Privacy
share
A point-of-interest (POI) recommendation system plays an important role in location-based services (LBS) because it can help people to explore new locations and promote advertisers to launch ads to target users. Exiting POI recommendation methods need users' raw check-in data, which can raise location privacy breaches. Even worse, several privacy-preserving recommendation systems could not utilize the transition pattern in the human movement. To address these problems, we propose Successive Point-of-Interest REcommendation with Local differential privacy (SPIREL) framework. SPIREL employs two types of sources from users' check-in history: a transition pattern between two POIs and visiting counts of POIs. We propose a novel objective function for learning the user-POI and POI-POI relationships simultaneously. We further propose two privacy-preserving mechanisms to train our recommendation system. Experiments using two public datasets demonstrate that SPIREL achieves better POI recommendation quality while preserving stronger privacy for check-in history.
READ FULL TEXT