[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-195406-105":53,"doc-detail-195406-en":126},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":119,"head_meta":121,"extra_data":123,"updated_unix":125},105,"en","predicting-next-item-recommendation-with-temporal-aware-and-feature-interaction-attention-network","Predicting Next-Item Recommendation with Temporal Aware and Feature Interaction Attention Network","","This paper introduces a novel Temporal Aware and Feature Interaction Attention Network (TLSAN) for next-item recommendation, designed to capture complex temporal dependencies and feature interactions in user behavior sequences. The TLSAN model leverages both long-term and short-term user behavior sequences to provide more accurate predictions of the next item a user might be interested in. The model incorporates several key components, including long-term customer shopping behavior embeddings, time and contextual history embeddings, and feature-wise attention layers for both long-term and short-term sequences. These components work in concert to model the dynamic nature of user preferences and the influence of historical interactions on future choices. Experimental results on several benchmark datasets demonstrate that TLSAN significantly outperforms existing state-of-the-art methods in terms of Recall@K and Precision@K metrics, highlighting its effectiveness in capturing intricate sequential patterns and feature relationships within user behavior data for enhanced recommendation accuracy. The study also presents a comparative analysis with models like CSAN, ATRank, Bi-LSTM, and PACA, further validating the superiority of the proposed TLSAN approach.",{"@graph":63,"@context":118},[64,80,101],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":51,"@type":70,"position":76},"https://docshare.wps.com/template/general/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/predicting-next-item-recommendation-with-temporal-aware-and-feature-interaction-attention-network/195406/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/predicting-next-item-recommendation-with-temporal-aware-and-feature-interaction-attention-network/195406.png","ImageObject",442,249,{"name":88,"@type":89},"Theodora","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-09-28","2026-09-03",true,{"@type":98,"interactionType":99,"userInteractionCount":76},"InteractionCounter",{"@type":100},"ViewAction",{"@type":102,"mainEntity":103},"FAQPage",[104,110,114],{"name":105,"@type":106,"acceptedAnswer":107},"What is the primary goal of the TLSAN model?","Question",{"text":108,"@type":109},"The primary goal of the TLSAN model is to predict the next item a user is likely to interact with by effectively capturing complex temporal dependencies and feature interactions within user behavior sequences.","Answer",{"name":111,"@type":106,"acceptedAnswer":112},"What are the main components of the TLSAN model?",{"text":113,"@type":109},"The TLSAN model comprises long-term customer shopping behavior embeddings, time and contextual history embeddings, and feature-wise attention layers for both long-term and short-term user behavior sequences.",{"name":115,"@type":106,"acceptedAnswer":116},"How does TLSAN compare to other recommendation models?",{"text":117,"@type":109},"Experimental results show that TLSAN significantly outperforms other state-of-the-art methods, including CSAN, ATRank, Bi-LSTM, and PACA, in terms of Recall@K and Precision@K metrics.","https://schema.org",{"og:url":78,"og:type":120,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":122,"canonical":78},"index,follow",{"doc_id":124,"site_id":56},195406,1788448186,{"code":4,"msg":5,"data":127},{"doc_id":124,"user_id":128,"nickname":88,"user_avatar":129,"doc_module":9,"category_id":50,"category_name":51,"doc_title":59,"doc_description":61,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":76,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":135,"language":136,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":137,"faqs":138,"seo_title":139,"seo_description":61,"update_tm":125,"read_time":73},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","| Datasets | LLM Recommender | CSAN | ATRank | Bi-LSTM | PACA | TLSAN | C-TLSAN |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| CDs and Vinyl | 0.827 | 0.813 | 0.889 | 0.881 | 0.801 | 0.942 | 0.938 |\n| Clothing Shoes and Jewelry | 0.639 | 0.761 | 0.663 | 0.668 | 0.798 | 0.927 | 0.938 |\n| Digital-Music | 0.808 | 0.729 | 0.825 | 0.792 | 0.963 | 0.972 | 0.974 |\n| Office Products | 0.516 | 0.824 | 0.921 | 0.856 | 0.910 | 0.969 | 0.976 |\n| Movies and TV | 0.813 | 0.797 | 0.860 | 0.824 | 0.806 | 0.879 | 0.909 |\n| Beauty | 0.618 | 0.727 | 0.806 | 0.773 | 0.859 | 0.925 | 0.947 |\n| Home and Kitchen | 0.592 | 0.702 | 0.736 | 0.684 | 0.788 | 0.865 | 0.895 |\n| Video Games | 0.587 | 0.807 | 0.870 | 0.820 | 0.917 | 0.914 | 0.933 |\n| Toys and Games | 0.678 | 0.812 | 0.829 | 0.775 | 0.861 | 0.922 | 0.936 |\n| Electronics | 0.587 | 0.811 | 0.841 | 0.811 | 0.835 | 0.894 | 0.913 |\n\n\n|  | Recall @10 |  | Precision @10 |  |\n| --- | --- | --- | --- | --- |\n| Dataset | TLSAN | cTLSAN | TLSAN | cTLSAN |\n| CDs_and_Vinyl | 4.12% | 8.57% | 0.41% | 0.86% |\n| Digital-Music | 16.38% | 24.87% | 1.64% | 2.49% |\n| Office_Products | 31.25% | 46.09% | 3.13% | 4.61% |\n| Movies_and_TV_5 | 1.64% | 6.04% | 0.16% | 0.60% |\n| Beauty | 11.27% | 18.54% | 1.13% | 1.85% |\n| Home_and_Kitchen | 7.27% | 12.90% | 0.73% | 1.29% |\n| Video_Games | 7.88% | 12.28% | 0.79% | 1.23% |\n| Toys_and_Games | 10.53% | 20.24% | 1.05% | 2.02% |\n| Electronics | 4.72% | 8.51% | 0.47% | 0.85% |","cbCailSE5qRvG5Is","https://ap.wps.com/l/cbCailSE5qRvG5Is","pdf",677893,6,"English","# TLSAN Model Architecture\n# Experimental Results\n## Recall@K Performance\n## Precision@K Performance","[{\"question\":\"What is the primary goal of the TLSAN model?\",\"answer\":\"The primary goal of the TLSAN model is to predict the next item a user is likely to interact with by effectively capturing complex temporal dependencies and feature interactions within user behavior sequences.\"},{\"question\":\"What are the main components of the TLSAN model?\",\"answer\":\"The TLSAN model comprises long-term customer shopping behavior embeddings, time and contextual history embeddings, and feature-wise attention layers for both long-term and short-term user behavior sequences.\"},{\"question\":\"How does TLSAN compare to other recommendation models?\",\"answer\":\"Experimental results show that TLSAN significantly outperforms other state-of-the-art methods, including CSAN, ATRank, Bi-LSTM, and PACA, in terms of Recall@K and Precision@K metrics.\"}]","Predicting Next-Item Recommendation with Temporal Aware and Feature Interaction Attention Network | PDF"]