{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T19:02:08Z","timestamp":1757703728668,"version":"3.41.2"},"reference-count":57,"publisher":"Emerald","issue":"2","license":[{"start":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T00:00:00Z","timestamp":1734912000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJICC"],"published-print":{"date-parts":[[2025,5,8]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>When recommending products to consumers, it is important to be able to accurately predict how consumers will rate them. However, existing collaborative filtering models are difficult to achieve a balance between rating prediction accuracy and complexity. Therefore, the purpose of this paper is to propose an accurate and effective model to predict users\u2019 ratings of products for the accurate recommendation of products to users.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>First, we introduce an attention mechanism that dynamically assigns weights to user preferences, highlighting key interaction information and enhancing the model\u2019s understanding of user behavior. Second, a fold embedding strategy is employed to segment user interaction data, increasing the information density of each subset while reducing the complexity of the attention mechanism. Finally, a masking strategy is integrated to mitigate overfitting by concealing portions of user-item interactions, thereby improving the model\u2019s generalization ability.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>The experimental results demonstrate that the proposed model significantly minimizes prediction error across five real-world datasets. On average, the evaluation metrics root mean square error (RMSE) and mean absolute error (MAE) are reduced by 9.11 and 13.3%, respectively. Additionally, the Friedman test results confirm that these improvements are statistically significant. Consequently, the proposed model more accurately captures the intrinsic correlation between users and products, leading to a substantial reduction in prediction error.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>We propose a novel collaborative filtering model to learn the user-item interaction matrix effectively. Additionally, we introduce a fold embedding strategy to reduce the computational resource consumption of the attention mechanism. Finally, we implement a masking strategy to encourage the model to focus on key features and patterns, thereby mitigating overfitting.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ijicc-08-2024-0362","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T01:24:26Z","timestamp":1734657866000},"page":"259-281","source":"Crossref","is-referenced-by-count":1,"title":["Fold embedding and attention-based collaborative filtering with masking strategy for consumer products rating prediction"],"prefix":"10.1108","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2322-0811","authenticated-orcid":false,"given":"Jiaqi","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingwei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3039-9054","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeshui","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"key2025050804574798400_ref001","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.5555\/3495724.3495883","article-title":"Language models are few shot learners","year":"2020"},{"issue":"12","key":"key2025050804574798400_ref002","doi-asserted-by":"publisher","first-page":"2394","DOI":"10.1109\/TSMC.2017.2695158","article-title":"Opinion dynamics-based group recommender systems","volume":"48","year":"2017","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"key2025050804574798400_ref003","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119797","article-title":"NT-DPTC: a non-negative temporal dimension preserved tensor completion model for missing traffic data imputation","volume":"653","year":"2024","journal-title":"Information Sciences"},{"key":"key2025050804574798400_ref004","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119420","article-title":"SARWAS: deep ensemble learning techniques for sentiment-based recommendation system","volume":"216","year":"2023","journal-title":"Expert Systems with Applications"},{"journal-title":"arXiv","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","year":"2018","key":"key2025050804574798400_ref005"},{"journal-title":"arXiv","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","year":"2020","key":"key2025050804574798400_ref006"},{"issue":"3","key":"key2025050804574798400_ref007","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1109\/TCOMM.2018.2881117","article-title":"Learning-aided physical layer authentication as an intelligent process","volume":"67","year":"2018","journal-title":"IEEE Transactions on Communications"},{"key":"key2025050804574798400_ref008","unstructured":"Funk, S. (2006), \u201cNetflix update: try this at home\u201d, available at: https:\/\/sifter.org\/\u223csimon\/journal\/20061211.html"},{"issue":"3","key":"key2025050804574798400_ref009","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1109\/TNNLS.2019.2909432","article-title":"Adaptive deep modeling of users and items using side information for recommendation","volume":"31","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"key2025050804574798400_ref010","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2827872","article-title":"The MovieLens datasets: history and context","volume":"5","year":"2015","journal-title":"ACM Transactions on Interactive Intelligent Systems (TIIS)"},{"key":"key2025050804574798400_ref011","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1145\/3038912.3052569","article-title":"Neural collaborative filtering","year":"2017"},{"issue":"8","key":"key2025050804574798400_ref012","doi-asserted-by":"publisher","first-page":"2791","DOI":"10.1109\/TNNLS.2018.2890117","article-title":"Fast matrix factorization with nonuniform weights on missing data","volume":"31","year":"2019","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"key2025050804574798400_ref013","doi-asserted-by":"publisher","first-page":"16000","DOI":"10.1109\/CVPR52688.2022.01553","article-title":"Masked autoencoders are scalable vision learners","year":"2022"},{"issue":"1","key":"key2025050804574798400_ref014","doi-asserted-by":"publisher","first-page":"3259","DOI":"10.1109\/TCE.2023.3314537","article-title":"Heterogeneous graph convolutional network for E-commerce product recommendation with adaptive denoising training","volume":"70","year":"2023","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"key2025050804574798400_ref015","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114528","article-title":"CNN with depthwise separable convolutions and combined Kernels for rating prediction","volume":"170","year":"2021","journal-title":"Expert Systems with Applications"},{"journal-title":"arXiv","article-title":"Adam: a method for stochastic optimization","year":"2014","key":"key2025050804574798400_ref016"},{"key":"key2025050804574798400_ref017","doi-asserted-by":"crossref","unstructured":"Koren, Y., Rendle, S. and Bell, R. (2021), \u201cAdvances in collaborative filtering\u201d, in Recommender Systems Handbook, pp.\u00a091-142, doi: 10.1007\/978-1-0716-2197-4_3.","DOI":"10.1007\/978-1-0716-2197-4_3"},{"issue":"2","key":"key2025050804574798400_ref018","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1109\/JAS.2019.1911417","article-title":"Graph regularized Lp smooth non-negative matrix factorization for data representation","volume":"6","year":"2019","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"2","key":"key2025050804574798400_ref019","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1109\/TSC.2022.3177316","article-title":"A momentum-accelerated Hessian-vector-based latent factor analysis model","volume":"16","year":"2022","journal-title":"IEEE Transactions on Services Computing"},{"issue":"7","key":"key2025050804574798400_ref020","doi-asserted-by":"publisher","first-page":"2956","DOI":"10.1109\/TKDE.2019.2961666","article-title":"Social recommendation with learning personal and social latent factors","volume":"33","year":"2019","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"key2025050804574798400_ref021","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1145\/3308558.3313497","article-title":"Feature generation by convolutional neural network for click-through rate prediction","year":"2019"},{"key":"key2025050804574798400_ref022","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","year":"2021"},{"issue":"3","key":"key2025050804574798400_ref023","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1109\/TNNLS.2015.2415257","article-title":"A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method","volume":"27","year":"2015","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"5","key":"key2025050804574798400_ref024","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TII.2017.2766528","article-title":"An inherently nonnegative latent factor model for high-dimensional and sparse matrices from industrial applications","volume":"14","year":"2017","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"1","key":"key2025050804574798400_ref025","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.2018.2875452","article-title":"A fast non-negative latent factor model based on generalized momentum method","volume":"51","year":"2018","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"1","key":"key2025050804574798400_ref026","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TCE.2023.3277549","article-title":"DSMN: an improved recommendation model for capturing the multiplicity and dynamics of consumer interests","volume":"70","year":"2023","journal-title":"IEEE Transactions on Consumer Electronics"},{"issue":"4","key":"key2025050804574798400_ref027","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1108\/IJICC-11-2021-0257","article-title":"A multi-preference integrated algorithm (MPIA) for the deep learning-based recommender framework (DLRF)","volume":"15","year":"2022","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"key":"key2025050804574798400_ref028","first-page":"2","article-title":"Masked transformer for neighhourhood-aware click-through rate prediction","year":"2022","journal-title":"arXiv, preprint arXiv:2201.13311"},{"key":"key2025050804574798400_ref029","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118164","article-title":"Hierarchical attention and transformers for automatic movie rating","volume":"209","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"key2025050804574798400_ref030","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.1109\/ICDM.2016.0151","article-title":"Product-based neural networks for user response prediction","year":"2016"},{"key":"key2025050804574798400_ref031","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1145\/1273496.1273596","article-title":"Restricted Boltzmann machines for collaborative filtering","year":"2007"},{"key":"key2025050804574798400_ref032","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1145\/371920.372071","article-title":"Item-based collaborative filtering recommendation algorithms","year":"2001"},{"key":"key2025050804574798400_ref033","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1145\/2740908.2742726","article-title":"AutoRec: autoencoders meet collaborative filtering","year":"2015"},{"issue":"1","key":"key2025050804574798400_ref034","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/JAS.2018.7511189","article-title":"Randomized latent factor model for high-dimensional and sparse matrices from industrial applications","volume":"6","year":"2018","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"key2025050804574798400_ref035","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119071","article-title":"Deep neural network-based multi-stakeholder recommendation system exploiting multi-criteria ratings for preference learning","volume":"213","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"key2025050804574798400_ref036","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1145\/3357384.3357925","article-title":"AutoInt: automatic feature interaction learning via self-attentive neural networks","year":"2019"},{"key":"key2025050804574798400_ref037","doi-asserted-by":"publisher","first-page":"6000","DOI":"10.5555\/3295222.3295349","article-title":"Attention is all you need","year":"2017"},{"key":"key2025050804574798400_ref038","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3124749.3124754","article-title":"Deep and cross network for ad click predictions","year":"2017"},{"key":"key2025050804574798400_ref039","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1609\/aaai.v32i1.11251","article-title":"Confidence-aware matrix factorization for recommender systems","year":"2018"},{"key":"key2025050804574798400_ref040","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118395","article-title":"Session-based recommendation with time-aware neural attention network","volume":"210","year":"2022","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"key2025050804574798400_ref041","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1108\/IJICC-01-2024-0016","article-title":"UICF: a new user-item composite filtering recommendation framework by leveraging temporal semantics","volume":"17","year":"2024","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"key":"key2025050804574798400_ref042","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1145\/2835776.2835837","article-title":"Collaborative denoising auto-encoders for top-n recommender systems","year":"2016"},{"key":"key2025050804574798400_ref043","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.knosys.2018.01.003","article-title":"Dual-regularized matrix factorization with deep neural networks for recommender systems","volume":"145","year":"2018","journal-title":"Knowledge-Based Systems"},{"issue":"10","key":"key2025050804574798400_ref044","doi-asserted-by":"publisher","first-page":"5775","DOI":"10.1109\/TNNLS.2021.3071392","article-title":"An L1-and-L2-norm-oriented latent factor model for recommender systems","volume":"33","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"key2025050804574798400_ref045","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1109\/TNNLS.2022.3200009","article-title":"A prediction-sampling-based multilayer-structured latent factor model for accurate representation to high-dimensional and sparse data","volume":"35","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"key2025050804574798400_ref046","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TETCI.2024.3437370","article-title":"An outlier-resilient autoencoder for representing high-dimensional and incomplete data","year":"2024","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"key2025050804574798400_ref047","doi-asserted-by":"publisher","first-page":"3119","DOI":"10.5555\/3172077.3172324","article-title":"Attentional factorization machines: learning the weight of feature interactions via attention networks","year":"2017"},{"issue":"10","key":"key2025050804574798400_ref048","doi-asserted-by":"publisher","first-page":"11001","DOI":"10.1109\/TITS.2023.3279321","article-title":"HRST-LR: a Hessian regularization spatio-temporal low rank algorithm for traffic data imputation","volume":"24","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"key2025050804574798400_ref049","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-319-70087-8_20","article-title":"Hybrid collaborative recommendation via semi-autoencoder","year":"2017"},{"issue":"1","key":"key2025050804574798400_ref050","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3285029","article-title":"Deep learning-based recommender system: a survey and new perspectives","volume":"52","year":"2019","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"key2025050804574798400_ref051","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116717","article-title":"AENAR: an aspect-aware explainable neural attentional recommender model for rating predication","volume":"198","year":"2022","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"key2025050804574798400_ref052","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/MITS.2019.2953557","article-title":"Routing schemes in software-defined vehicular networks: design, open issues and challenges","volume":"13","year":"2020","journal-title":"IEEE Intelligent Transportation Systems Magazine"},{"issue":"5","key":"key2025050804574798400_ref053","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/MNET.011.1900587","article-title":"Intelligent digital twin-based software-defined vehicular networks","volume":"34","year":"2020","journal-title":"IEEE Network"},{"issue":"11","key":"key2025050804574798400_ref054","doi-asserted-by":"publisher","first-page":"7871","DOI":"10.1109\/TII.2021.3059640","article-title":"Vehicular computation offloading for industrial mobile edge computing","volume":"17","year":"2021","journal-title":"IEEE Transactions on Industrial Informatics"},{"issue":"8","key":"key2025050804574798400_ref055","doi-asserted-by":"publisher","first-page":"13275","DOI":"10.1109\/TITS.2021.3123276","article-title":"A novel prediction-based temporal graph routing algorithm for software-defined vehicular networks","volume":"23","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"10","key":"key2025050804574798400_ref056","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TITS.2024.3398602","article-title":"Overtaking feasibility prediction for mixed connected and connectionless vehicles","volume":"25","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems (TITS)"},{"issue":"1","key":"key2025050804574798400_ref057","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1108\/IJICC-09-2019-0103","article-title":"A novel movies recommendation algorithm based on reinforcement learning with DDPG policy","volume":"13","year":"2020","journal-title":"International Journal of Intelligent Computing and Cybernetics"}],"container-title":["International Journal of Intelligent Computing and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-08-2024-0362\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-08-2024-0362\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:54:48Z","timestamp":1753397688000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijicc\/article\/18\/2\/259-281\/1263542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":57,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,12,23]]},"published-print":{"date-parts":[[2025,5,8]]}},"alternative-id":["10.1108\/IJICC-08-2024-0362"],"URL":"https:\/\/doi.org\/10.1108\/ijicc-08-2024-0362","relation":{},"ISSN":["1756-378X","1756-3798"],"issn-type":[{"type":"print","value":"1756-378X"},{"type":"electronic","value":"1756-3798"}],"subject":[],"published":{"date-parts":[[2024,12,23]]}}}