{"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/inter-session-modeling-for-session-based","title":"Inter-Session Modeling for Session-Based Recommendation","arxiv_id":"1706.07506","date":"2017-06-22","proceeding":null,"authors":["Massimiliano Ruocco","Ole Steinar Lillestøl Skrede","Helge Langseth"],"abstract":"In recent years, research has been done on applying Recurrent Neural Networks\n(RNNs) as recommender systems. Results have been promising, especially in the\nsession-based setting where RNNs have been shown to outperform state-of-the-art\nmodels. In many of these experiments, the RNN could potentially improve the\nrecommendations by utilizing information about the user's past sessions, in\naddition to its own interactions in the current session. A problem for\nsession-based recommendation, is how to produce accurate recommendations at the\nstart of a session, before the system has learned much about the user's current\ninterests. We propose a novel approach that extends a RNN recommender to be\nable to process the user's recent sessions, in order to improve\nrecommendations. This is done by using a second RNN to learn from recent\nsessions, and predict the user's interest in the current session. By feeding\nthis information to the original RNN, it is able to improve its\nrecommendations. Our experiments on two different datasets show that the\nproposed approach can significantly improve recommendations throughout the\nsessions, compared to a single RNN working only on the current session. The\nproposed model especially improves recommendations at the start of sessions,\nand is therefore able to deal with the cold start problem within sessions.","url_abs":"http://arxiv.org/abs/1706.07506v1","url_pdf":"http://arxiv.org/pdf/1706.07506v1.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":"inter-session-modeling-for-session-based","repo_url":"https://github.com/olesls/master_thesis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}