{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-novel-approach-for-venue-recommendation","title":"A novel approach for venue recommendation using cross-domain techniques","arxiv_id":"1809.09864","date":"2018-09-26","proceeding":null,"authors":["Pablo Sánchez","Alejandro Bellogín"],"abstract":"Finding the next venue to be visited by a user in a specific city is an\ninteresting, but challenging, problem. Different techniques have been proposed,\ncombining collaborative, content, social, and geographical signals; however it\nis not trivial to decide which tech- nique works best, since this may depend on\nthe data density or the amount of activity logged for each user or item. At the\nsame time, cross-domain strategies have been exploited in the recommender\nsystems literature when dealing with (very) sparse situations, such as those\ninherently arising when recommendations are produced based on information from\na single city.\n  In this paper, we address the problem of venue recommendation from a novel\nperspective: applying cross-domain recommenda- tion techniques considering each\ncity as a different domain. We perform an experimental comparison of several\nrecommendation techniques in a temporal split under two conditions:\nsingle-domain (only information from the target city is considered) and cross-\ndomain (information from many other cities is incorporated into the\nrecommendation algorithm). For the latter, we have explored two strategies to\ntransfer knowledge from one domain to another: testing the target city and\ntraining a model with information of the k cities with more ratings or only\nusing the k closest cities.\n  Our results show that, in general, applying cross-domain by proximity\nincreases the performance of the majority of the recom- menders in terms of\nrelevance. This is the first work, to the best of our knowledge, where so many\ndomains (eight) are combined in the tourism context where a temporal split is\nused, and thus we expect these results could provide readers with an overall\npicture of what can be achieved in a real-world environment.","url_abs":"http://arxiv.org/abs/1809.09864v1","url_pdf":"http://arxiv.org/pdf/1809.09864v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-novel-approach-for-venue-recommendation","repo_url":"https://bitbucket.org/PabloSanchezP/TempCDSeqEval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}