{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T12:25:17Z","timestamp":1766492717679,"version":"build-2065373602"},"reference-count":22,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>With the rapid development of the global digital economy, cross-border e-commerce has rapidly emerged and developed at a high speed, and has become a crucial bridge connecting global markets. This research focuses on the cross-border e-commerce sector of outdoor sports products, in response to the common problems in the cross-border e-commerce field, such as \u201cinformation overload\u201d and \u201cinsufficient recommendation accuracy,\u201d a personalized recommendation optimization framework integrating customer value segmentation and collaborative filtering is proposed. Based on the classic RFM model, the purchase quantity indicator (Quantity) is introduced to construct the RFMQ model, thereby more comprehensively characterizing user behavior characteristics. Further, the customer value stratification is achieved by using the indicator segmentation method and the K-means clustering algorithm, and a differentiated collaborative filtering recommendation mechanism is designed based on the segmented groups. Through a five-fold cross-validation experiment, it is shown that the proposed method significantly outperforms the traditional collaborative filtering model in the TOPN recommendation task. Specifically, when the number of recommended products is between 3 and 7, the RFMQ recommendation model based on indicator segmentation performs best in terms of F1 score (for example, when TOPN = 5, the F1 value increases from 0.1709 to 0.3093), and the method based on K-means clustering also shows a stable improvement (with the F1 value reaching 0.267 at the same time). The results indicate that the indicator segmentation method has a significant advantage in smaller recommendation quantity scenarios. This study verifies the effectiveness of the RFMQ model in customer segmentation and recommendation performance optimization, providing an operational solution for e-commerce platforms to implement precise marketing, enhance user stickiness and commercial competitiveness, and is particularly suitable for low-cost and high-efficiency personalized recommendation scenarios of small and medium-sized enterprises.<\/jats:p>","DOI":"10.3389\/fdata.2025.1680669","type":"journal-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T04:15:02Z","timestamp":1760415302000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Research on optimization of personalized recommendation method based on RFMQ model\u2014 taking outdoor sports products in cross-border e-commerce as an example"],"prefix":"10.3389","volume":"8","author":[{"given":"Qianlan","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chupeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zubai","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangxizi","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niannian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingxian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"B1","unstructured":"Beretzky\n              E.\n            \n            \n              Hausmann\n              L.\n            \n            \n              W\u00f6lfel\n              T.\n            \n            \n              Zimmermann\n              T.\n            \n          \n          Signed, Sealed, and Delivered: Unpacking The Cross-Border Parcel Market's Promise\n          \n          2022"},{"key":"B2","doi-asserted-by":"publisher","first-page":"122327","DOI":"10.1016\/j.ins.2025.122327","article-title":"Data-driven strategic customer segmentation considering cart abandonment behavior: insights from e-grocery delivery platforms","volume":"718","author":"Chavhan","year":"2025","journal-title":"Inf. Sci."},{"key":"B3","doi-asserted-by":"publisher","first-page":"3469","DOI":"10.2478\/amns-2024-3469","article-title":"Research on music teaching content design based on intelligent algorithm optimization under constructivism theory","volume":"9","author":"Chen","year":"2024","journal-title":"Appl. Math. Nonlinear Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3389\/fdata.2019.00049","article-title":"Attribute-aware recommender system based on collaborative filtering: survey and classification","volume":"2","author":"Chen","year":"2020","journal-title":"Front. Big Data"},{"key":"B5","year":"2023","journal-title":"China Sports and Fitness Products IndusBlue Book."},{"key":"B6","unstructured":"\u201cAn improved collaborative filtering algorithm combining content-based algorithm and user activity,\u201d\n          \n          88\n          91\n          \n            \n              Fan\n              J.\n            \n            \n              Pan\n              W.\n            \n            \n              Jiang\n              L\n            \n          \n          IEEE\n          \n          2014"},{"key":"B7","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1145\/138859.138867","article-title":"Using collaborative filtering to weave an information tapestry","volume":"35","author":"Goldberg","year":"1992","journal-title":"Commun. ACM"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.techsoc.2025.102917","article-title":"The power of digital nativeness: exploring how millennials mitigate psychic distance in cross-border electronic commerce","author":"Han","year":"2025","journal-title":"Technol. Soc. 82:"},{"key":"B9","doi-asserted-by":"publisher","first-page":"97","DOI":"10.13266\/j.issn.0252-3116.2016.23.013","article-title":"Comparative study of information service quality of domestic e-commerce website recommendation systems: a case study of Taobao, JD, and Amazon","volume":"60","author":"Hong","year":"2016","journal-title":"Libr. Inf. Serv."},{"key":"B10","doi-asserted-by":"crossref","DOI":"10.1002\/dac.5161","article-title":"Geographical POI recommendation for Internet of Things: a federated learning approach using matrix factorization","volume-title":"Int. J. Commun. Syst.","author":"Huang","year":"2022"},{"key":"B11","volume-title":"Strategic Database Marketing","author":"Hughes","year":"1994"},{"key":"B12","doi-asserted-by":"publisher","first-page":"974072","DOI":"10.3389\/fdata.2023.974072","article-title":"Personalized diversification of complementary recommendations with user preference in online grocery","volume":"6","author":"Ma","year":"2023","journal-title":"Front. Big Data"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1249997","DOI":"10.3389\/fdata.2023.1249997","article-title":"Differential privacy in collaborative filtering recommender systems: a review","volume":"6","author":"M\u00fcllner","year":"2023","journal-title":"Front. Big Data"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.14097\/j.cnki.5392\/2019.24.008","article-title":"Research on personalized recommendation models and applications for retail enterprises based on the RFMQ model","author":"Niu","year":"2019","journal-title":"Mod. Bus."},{"key":"B15","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s10462-021-10043-x","article-title":"News recommender system: a review of recent progress, challenges, and opportunities","volume":"55","author":"Raza","year":"2022","journal-title":"Artif. Intell. Rev."},{"key":"B16","doi-asserted-by":"publisher","first-page":"152","DOI":"10.4304\/jait.2.3.152-158","article-title":"Hybrid personalized recommender system using fast k-medoids clustering algorithm","volume":"2","author":"Shinde","year":"2011","journal-title":"J. Adv. Inf. Technol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1599704","DOI":"10.3389\/fdata.2025.1599704","article-title":"Collaborative filtering based on nonnegative\/binary matrix factorization","volume":"7","author":"Terui","year":"2025","journal-title":"Front. Big Data"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5","DOI":"10.16099\/j.cnki.jsus.2015.02.002","article-title":"Research on the upgrading of China's sports equipment industry from the perspective of the global value chain","volume":"39","author":"Wang","year":"2015","journal-title":"J. Shanghai Univ. Sport"},{"key":"B19","doi-asserted-by":"publisher","first-page":"9982484","DOI":"10.1155\/2021\/9982484","article-title":"User value identification based on improved RFM model and K-means++ algorithm for complex data analysis","volume":"2021","author":"Wu","year":"2021","journal-title":"Wirel. Commun. Mobile Comput."},{"key":"B20","doi-asserted-by":"publisher","first-page":"128465","DOI":"10.1016\/j.eswa.2025.128465","article-title":"Enhancing customer retention in Online Retail through churn prediction: a hybrid RFM, K-means, and deep neural network approach","volume":"290","author":"Zaghloul","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B21","doi-asserted-by":"publisher","first-page":"166","DOI":"10.13833\/j.issn.1007-7634.2020.09.025","article-title":"Research hotspots and implications of user models in recommendation systems: a knowledge graph analysis based on core literature from the past decade","volume":"38","author":"Zhou","year":"2020","journal-title":"Inf. Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"4155","DOI":"10.3233\/JIFS-200737","article-title":"Customer stratification theory and value evaluation\u2014analysis based on improved RFM model","volume":"40","author":"Zong","year":"2021","journal-title":"J. Intell. Fuzzy Syst."}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1680669\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T04:15:07Z","timestamp":1760415307000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2025.1680669\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":22,"alternative-id":["10.3389\/fdata.2025.1680669"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2025.1680669","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"article-number":"1680669"}}