Using multi-criteria decision making for personalized point-of-interest recommendations

Abstract

Location-based business review (LBBR) sites (e.g., Yelp) provide us a possibility to recommend new points of interest (POIs) for users. The geographical position and category of POIs have been considered as two major factors in modeling users' preferences. However, it is argued that the user's visiting behaviors are also affected by the attributes of POIs, which reflect the basic features of the POIs. Besides, a user may have different preference levels on the same POI with regard to different criteria. To this end, we propose a new personalized POI recommendation framework using Multi-Criteria Decision Making (MCDM). Firstly, preference models are built for the user's geographical, category, and attribute preferences. Then, an MCDM-based recommendation framework is designed to iteratively combine the user's preferences on the three criteria and select the top-N POIs as a recommendation list. Experimental results show that our framework not only outperforms the state-of-the-art POI recommendation techniques, but also provides a better trade-off mechanism for MCDM than the weighted sum approach.