An experimental evaluation of point-of-interest recommendation in location-based social networks

TLDR

POI recommendation is a key service for LBSNs, yet systematic comparison of existing systems remains lacking. The study aims to give readers a comprehensive view of POI recommendation by evaluating 12 state‑of‑the‑art models. We evaluate 12 state‑of‑the‑art POI recommendation models. The evaluation reveals key insights that improve understanding and application of POI recommendation models across scenarios.

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 all-around evaluation of 12 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.