An Experimental Evaluation of Point-of-interest Recommendation
in Location-based Social Networks [full version]



1. Abstract

Point-of-interest (POI) recommendation is an important service to Location-Based Social Networks (LBSNs) that can benefit both users and businesses. In recent years, a number of POI recommender systems have been proposed, but there is still a lack of systematical comparison thereof. In this paper, we provide an allaround evaluation of 11 state-of-the-art POI recommendation models. From the evaluation, we obtain several important findings, based on which we can better understand and utilize POI recommendation models in various scenarios. We anticipate this work to provide readers with an overall picture of the cutting-edge research on POI recommendation.

2. Source codes

In this paper, we evaluate 12 state-of-the-art models in POI recommendation. Below are source codes of thoses models, each of which is either provied by authors or implemented by us. For how to use the code, please check README.

3. Datasets

We perform the evaluation on three public datasets:

4. Authors