Point-of-Interest Recommender Systems: A Survey from an Experimental Perspective PABLO SÁNCHEZ ∗ , Universidad Autónoma de Madrid, Spain ALEJANDRO BELLOGÍN, Universidad Autónoma de Madrid, Spain Point-of-Interest recommendation is an increasing research and developing area within the widely adopted technologies known as Recommender Systems. Among them, those that exploit information coming from Location-Based Social Networks (LBSNs) are very popular nowadays and could work with diferent information sources, which pose several challenges and research questions to the community as a whole. We present a systematic review focused on the research done in the last 10 years about this topic. We discuss and categorize the algorithms and evaluation methodologies used in these works and point out the opportunities and challenges that remain open in the feld. More specifcally, we report the leading recommendation techniques and information sources that have been exploited more often (such as the geographical signal and deep learning approaches) while we also alert about the lack of reproducibility in the feld that may hinder real performance improvements. CCS Concepts: · Information systems → Retrieval models and ranking; Recommender systems; Re- trieval efectiveness. Additional Key Words and Phrases: Recommender systems, point-of-interest recommendation, location-based social network, evaluation methodology, reproducibility ACM Reference Format: Pablo Sánchez and Alejandro Bellogín. 2021. Point-of-Interest Recommender Systems: A Survey from an Experimental Perspective . ACM Comput. Surv. 1, 1 (June 2021), 39 pages. https://doi.org/10.1145/1122445. 1122456 1 INTRODUCTION Recommender Systems (RSs) have risen as technological solutions to the information overload, as they help users to flter the most interesting items (in whatever domain the RS is being deployed) according to their preferences. Moreover, in the Internet era, they have become indispensable due to their ability to process large amounts of information and make personalized recommendations to users by learning their interests and tastes [126]. However, they serve other purposes as well. They are particularly useful to aggregate user behavior, which is pervasive nowadays, very common and easier to obtain thanks to the Internet and the increasing and diversity of social networks dealing with diferent domains. This is in fact related to the universal applicability of general RSs, since classic RSs have been oriented towards recommending music or movies, but for some years now ∗ Both authors contributed equally to this research. Authors’ addresses: Pablo Sánchez, Information Retrieval Group, Universidad Autónoma de Madrid, Madrid, 28049, Spain, pablo.sanchezp@uam.es; Alejandro Bellogín, Information Retrieval Group, Universidad Autónoma de Madrid, Madrid, 28049, Spain, alejandro.bellogin@uam.es. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM. 0360-0300/2021/6-ART $15.00 https://doi.org/10.1145/1122445.1122456 ACM Comput. Surv., Vol. 1, No. 1, Article . Publication date: June 2021. arXiv:2106.10069v1 [cs.IR] 18 Jun 2021