{"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/evaluation-of-session-based-recommendation","title":"Evaluation of Session-based Recommendation Algorithms","arxiv_id":"1803.09587","date":"2018-03-26","proceeding":null,"authors":["Malte Ludewig","Dietmar Jannach"],"abstract":"Recommender systems help users find relevant items of interest, for example\non e-commerce or media streaming sites. Most academic research is concerned\nwith approaches that personalize the recommendations according to long-term\nuser profiles. In many real-world applications, however, such long-term\nprofiles often do not exist and recommendations therefore have to be made\nsolely based on the observed behavior of a user during an ongoing session.\nGiven the high practical relevance of the problem, an increased interest in\nthis problem can be observed in recent years, leading to a number of proposals\nfor session-based recommendation algorithms that typically aim to predict the\nuser's immediate next actions. In this work, we present the results of an\nin-depth performance comparison of a number of such algorithms, using a variety\nof datasets and evaluation measures. Our comparison includes the most recent\napproaches based on recurrent neural networks like GRU4REC, factorized Markov\nmodel approaches such as FISM or FOSSIL, as well as simpler methods based,\ne.g., on nearest neighbor schemes. Our experiments reveal that algorithms of\nthis latter class, despite their sometimes almost trivial nature, often perform\nequally well or significantly better than today's more complex approaches based\non deep neural networks. Our results therefore suggest that there is\nsubstantial room for improvement regarding the development of more\nsophisticated session-based recommendation algorithms.","url_abs":"http://arxiv.org/abs/1803.09587v2","url_pdf":"http://arxiv.org/pdf/1803.09587v2.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":"evaluation-of-session-based-recommendation","repo_url":"https://github.com/herrbilbo/hse-recsys-project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"evaluation-of-session-based-recommendation","repo_url":"https://github.com/mmaher22/iCV-SBR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"evaluation-of-session-based-recommendation","repo_url":"https://github.com/rn5l/session-rec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"session-based-recommendations","task_name":"Session-Based Recommendations"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.09587","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}