The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Personalized Recommendation Method of E-Commerce Products Based on In-Depth User Interest Portraits
Abstract
In dynamic e-commerce environments, researchers strive to understand users' interests and behaviors to enhance personalized product recommendations. Traditional collaborative filtering (CF) algorithms have encountered computational challenges such as similarity errors and user rating habits. This research addresses these issues by emphasizing user profiling techniques. This article proposes an innovative user profile updating technique that explores the key components of user profile (basic information, behavior, and domain knowledge). An enhanced kernel fuzzy mean clustering algorithm constructs a dynamic user portrait based on domain knowledge mapping. This dynamic portrait is combined with e-commerce personalized recommendation to improve the accuracy of inferring user interests, thus facilitating accurate recommendation on the platform. The method proposed in this article greatly improves the overall performance and provides strong support for developing smarter and more personalized e-commerce product recommendation systems.
Related Content
|
Ruixue Ma, Qiang Zhu.
© 2024.
14 pages.
|
|
Jingyi Li, Shaowu Bao.
© 2024.
15 pages.
|
|
Qingping Li, Ming Liu, Yao Zhang.
© 2024.
18 pages.
|
|
Liangqun Yang, Jian Li.
© 2024.
19 pages.
|
|
Nan Li.
© 2024.
20 pages.
|
|
Henan Zhang, Xiangzhe Liu.
© 2024.
12 pages.
|
|
Ye Aifen, Lin Shuwan, Wang Huan.
© 2024.
14 pages.
|
|
|