{"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/contextual-sequence-modeling-for","title":"Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks","arxiv_id":"1706.07684","date":"2017-06-23","proceeding":null,"authors":["Elena Smirnova","Flavian vasile"],"abstract":"Recommendations can greatly benefit from good representations of the user\nstate at recommendation time. Recent approaches that leverage Recurrent Neural\nNetworks (RNNs) for session-based recommendations have shown that Deep Learning\nmodels can provide useful user representations for recommendation. However,\ncurrent RNN modeling approaches summarize the user state by only taking into\naccount the sequence of items that the user has interacted with in the past,\nwithout taking into account other essential types of context information such\nas the associated types of user-item interactions, the time gaps between events\nand the time of day for each interaction. To address this, we propose a new\nclass of Contextual Recurrent Neural Networks for Recommendation (CRNNs) that\ncan take into account the contextual information both in the input and output\nlayers and modifying the behavior of the RNN by combining the context embedding\nwith the item embedding and more explicitly, in the model dynamics, by\nparametrizing the hidden unit transitions as a function of context information.\nWe compare our CRNNs approach with RNNs and non-sequential baselines and show\ngood improvements on the next event prediction task.","url_abs":"http://arxiv.org/abs/1706.07684v1","url_pdf":"http://arxiv.org/pdf/1706.07684v1.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":"contextual-sequence-modeling-for","repo_url":"https://gitlab.inf.unibz.it/tural-gurbanov/mapm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"session-based-recommendations","task_name":"Session-Based Recommendations"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.07684","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}