{"work":{"id":"9d4b6587-2e21-4e80-9580-2f993ff7903f","openalex_id":"https://openalex.org/W2262817822","doi":"10.48550/arxiv.1511.06939","arxiv_id":"1511.06939","raw_key":null,"title":"Session-based Recommendations with Recurrent Neural Networks","authors":null,"authors_text":"Bal\\'azs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, Domonkos Tikk","year":2015,"venue":"cs.LG","abstract":"We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.","external_url":"https://arxiv.org/abs/1511.06939","cited_by_count":559,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"1511.06939","created_at":"2026-05-10T00:29:47.608498+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Session-based Recommendations with Recurrent Neural Networks","render_title":"Session-based Recommendations with Recurrent Neural Networks"},"hub":{"state":{"work_id":"9d4b6587-2e21-4e80-9580-2f993ff7903f","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":84,"external_cited_by_count":559,"distinct_field_count":4,"first_pith_cited_at":"2019-06-21T16:02:41+00:00","last_pith_cited_at":"2026-07-02T12:50:45+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-07T05:09:47.977980+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":7},{"context_role":"method","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":7},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T17:59:48.156537+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","work_id":"cedb01b6-64b1-4cd7-a797-f157c3dc9930","shared_citers":4},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":4},{"title":"A survey on cross-domain sequential recommendation","work_id":"94f3b60a-bf2c-471d-a6b5-266bccef8521","shared_citers":4},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":4},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":4},{"title":"Self-attentive sequential recommendation","work_id":"e1cab8a9-3fce-4373-b2cd-7ef0a8024ab7","shared_citers":4},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":4},{"title":"Yu, Julian McAuley, and Caiming Xiong","work_id":"73865d7b-a96c-4942-805b-e30af34fd069","shared_citers":4},{"title":"arXiv preprint arXiv:2303.14524 , year=","work_id":"1dfcfce8-2b83-4076-b4bb-112f6b4f35a3","shared_citers":3},{"title":"arXiv preprint arXiv:2409.12740 , year=","work_id":"499540e4-4ba3-49f5-a144-6443fb4dbc1c","shared_citers":3},{"title":"Decoding matters: Addressing amplification bias and homogeneity issue for llm-based recommenda- tion.arXiv preprint arXiv:2406.14900","work_id":"4f764b83-75a8-4499-a977-d6af5dc0467f","shared_citers":3},{"title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","work_id":"d1a07d92-e045-4af2-a79f-c7b0112cf824","shared_citers":3},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":3},{"title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","work_id":"557f9e99-cb00-4dd2-92fd-67ddcddbb35d","shared_citers":3},{"title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","work_id":"0e0b7549-2bc4-4574-aa7f-588ffa16eaae","shared_citers":3},{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","work_id":"27adfcc9-2a67-43d6-a844-78309012411f","shared_citers":3},{"title":null,"work_id":"01ea95d6-a255-4604-9012-7e5e4d854425","shared_citers":3},{"title":null,"work_id":"a3b59ea7-bcde-458e-b32b-82850dae3b3a","shared_citers":3},{"title":null,"work_id":"1aa1ab49-1675-42d7-ad7d-972d1e6ed150","shared_citers":3},{"title":"Actionpiece: Contextually tokeniz- ing action sequences for generative recommendation","work_id":"2f83d746-aace-4e7a-b113-72265531d16d","shared_citers":2},{"title":"Advances in neural information processing systems , volume=","work_id":"1265447d-0324-4d07-abba-34fa29d172da","shared_citers":2},{"title":"A large language model enhanced conversational recommender system","work_id":"f2d9f760-3b30-41cc-bfef-557965ad20f9","shared_citers":2}],"time_series":[{"n":1,"year":2024},{"n":1,"year":2025},{"n":34,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:00:28.550255+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:00:41.550240+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Session-based Recommendations with Recurrent Neural Networks","claims":[{"claim_text":"We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be pro","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Session-based Recommendations with Recurrent Neural Networks because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:00:04.587620+00:00"}},"summary":{"title":"Session-based Recommendations with Recurrent Neural Networks","claims":[{"claim_text":"We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be pro","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Session-based Recommendations with Recurrent Neural Networks because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":6},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":6},{"title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","work_id":"cedb01b6-64b1-4cd7-a797-f157c3dc9930","shared_citers":4},{"title":"Adam: A Method for Stochastic Optimization","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","shared_citers":4},{"title":"A survey on cross-domain sequential recommendation","work_id":"94f3b60a-bf2c-471d-a6b5-266bccef8521","shared_citers":4},{"title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","work_id":"64019d00-0b11-4bbd-b173-b46c8fad0157","shared_citers":4},{"title":"Proximal Policy Optimization Algorithms","work_id":"240c67fe-d14d-4520-91c1-38a4e272ca19","shared_citers":4},{"title":"Self-attentive sequential recommendation","work_id":"e1cab8a9-3fce-4373-b2cd-7ef0a8024ab7","shared_citers":4},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":4},{"title":"Yu, Julian McAuley, and Caiming Xiong","work_id":"73865d7b-a96c-4942-805b-e30af34fd069","shared_citers":4},{"title":"arXiv preprint arXiv:2303.14524 , year=","work_id":"1dfcfce8-2b83-4076-b4bb-112f6b4f35a3","shared_citers":3},{"title":"arXiv preprint arXiv:2409.12740 , year=","work_id":"499540e4-4ba3-49f5-a144-6443fb4dbc1c","shared_citers":3},{"title":"Decoding matters: Addressing amplification bias and homogeneity issue for llm-based recommenda- tion.arXiv preprint arXiv:2406.14900","work_id":"4f764b83-75a8-4499-a977-d6af5dc0467f","shared_citers":3},{"title":"OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment","work_id":"d1a07d92-e045-4af2-a79f-c7b0112cf824","shared_citers":3},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":3},{"title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","work_id":"557f9e99-cb00-4dd2-92fd-67ddcddbb35d","shared_citers":3},{"title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","work_id":"0e0b7549-2bc4-4574-aa7f-588ffa16eaae","shared_citers":3},{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","work_id":"27adfcc9-2a67-43d6-a844-78309012411f","shared_citers":3},{"title":null,"work_id":"01ea95d6-a255-4604-9012-7e5e4d854425","shared_citers":3},{"title":null,"work_id":"a3b59ea7-bcde-458e-b32b-82850dae3b3a","shared_citers":3},{"title":null,"work_id":"1aa1ab49-1675-42d7-ad7d-972d1e6ed150","shared_citers":3},{"title":"Actionpiece: Contextually tokeniz- ing action sequences for generative recommendation","work_id":"2f83d746-aace-4e7a-b113-72265531d16d","shared_citers":2},{"title":"Advances in neural information processing systems , volume=","work_id":"1265447d-0324-4d07-abba-34fa29d172da","shared_citers":2},{"title":"A large language model enhanced conversational recommender system","work_id":"f2d9f760-3b30-41cc-bfef-557965ad20f9","shared_citers":2}],"time_series":[{"n":1,"year":2024},{"n":1,"year":2025},{"n":34,"year":2026}],"dependency_candidates":[]},"authors":[]}}