Identification of User Preferences and Personalized Recommendation Strategy in E-commerce Platforms

Anyi Chen

doi:10.54097/3fr7w812

Authors

Anyi Chen

DOI:

https://doi.org/10.54097/3fr7w812

Keywords:

E-commerce platform, Recommendation algorithm, User preference recognition, Personalized recommendation, Data privacy

Abstract

With the rapid development of e-commerce platforms, accurately identifying user preferences and providing personalized recommendations has become a key strategy to enhance user satisfaction and platform market competitiveness. This article starts with the definition of user preference recognition, analyzes the core challenges faced by the e-commerce field, such as data complexity, differences in user behavior, privacy and data confidentiality issues, and potential biases in recommendation algorithms. It also strategically explores how to improve the quality of personalized recommendations. By using big data analysis technology to accurately capture user preferences, strengthen privacy and security protection, optimize the fairness and transparency of recommendation algorithms, and improve user interaction feedback mechanisms, specific improvement measures are aimed at providing practical suggestions for the optimization of personalized recommendation systems in future e-commerce.

References

[1] Dong, Wen, Cao, Yixuan, Yu, Xiaoting. "Research on Personalized Intelligent Recommendation Method for Multimedia Videos Based on User Preferences." Electronic Design Engineering 32.11 (2024): 192-195.

[2] Li, Jiajun. "Personalized Information Recommendation Method for E-commerce Based on Spark Platform." Information Technology 47.10 (2023): 66-71.

[3] Wang, Huisun Dehong. "Personalized Learning Resource Recommendation Algorithm Based on Improved Graph Neural Network and User Preference Clustering." Journal of Heilongjiang University of Engineering 36.6 (2022): 30-34.

[4] Zhang, Wende, Zhang, Mengqi, Li, Chan, et al. "Research on Book Resource Recommendation Integrating User Preference." Intelligence Exploration 5 (2023): 33-38.

[5] Liu, Qiping, Yang, Ping. "Research on Recommendation Strategies for O2O Platforms Based on User Comment Sentiment Analysis." Journal of Hubei Second Normal University 40.11 (2023): 35-43.

[6] An, Jingmin, Li, Guanyu, Jiang, Wei, et al. "Interest Point Recommendation Based on User Activity Trajectory and Personalized Region Segmentation." Journal of Computer Science 6 (2022): 45.

[7] Fan, Wenfang, Wang, Qian. "Research on the Impact of Personalized Intelligent Recommendations on Users' Impulsive Purchase Intentions Online." Management Review 34.12 (2022): 146-156.

[8] Zhu, Hongqi, Wang, Cheng. "Research on Implicit Feedback Recommendation Application Based on E-commerce User Behavior." Computer and Modernization 11 (2023): 44-50.