Proceedings of the 3rd International Conference on Big Data Economy and Digital Management, BDEDM 2024, January 12–14, 2024, Ningbo, China

Research Article

Construction and Application of Cross-border E-commerce Customer Characteristic Analysis Model Based on Data Mining Technology

Download45 downloads
  • @INPROCEEDINGS{10.4108/eai.12-1-2024.2347212,
        author={Yijia  Yu and Qingxiu  Liu},
        title={Construction and Application of Cross-border E-commerce Customer Characteristic Analysis Model Based on Data Mining Technology},
        proceedings={Proceedings of the 3rd International Conference on Big Data Economy and Digital Management, BDEDM 2024, January 12--14, 2024, Ningbo, China},
        publisher={EAI},
        proceedings_a={BDEDM},
        year={2024},
        month={6},
        keywords={data mining technology; cross-border e-commerce; precision marketing; customer characteristic analysis model},
        doi={10.4108/eai.12-1-2024.2347212}
    }
    
  • Yijia Yu
    Qingxiu Liu
    Year: 2024
    Construction and Application of Cross-border E-commerce Customer Characteristic Analysis Model Based on Data Mining Technology
    BDEDM
    EAI
    DOI: 10.4108/eai.12-1-2024.2347212
Yijia Yu1,*, Qingxiu Liu1
  • 1: Chongqing College of Architecture and Technology
*Contact email: workforyu@126.com

Abstract

With the continuous development of digital information technology, the application of data mining technology in precision marketing of cross-border e-commerce platform has become more and more extensive, and it has become a key force to promote the reform of marketing model of cross-border e-commerce platform. However, the current direction of data mining mostly focuses on personalized recommendation of goods, and its application scope is single. In this regard, based on the actual needs of the current cross-border e-commerce platform, combined with data mining technology, this paper will build a set of customer feature analysis model to help cross-border e-commerce platform quickly acquire the target user groups and complete the user purchase forecast, so as to make the platform's operation plan and marketing measures more accurate and effective. Practice has proved that the customer feature analysis model integrates Logistic Regression, XGBoost, CatBoost and other algorithms, which can predict and analyze the user information, user attributes, user behavior and other feature information, and reflect the user's willingness to buy a certain kind of goods. At the same time, the model also supports K-means algorithm to cluster customer characteristics, so as to clarify the target user group of a certain kind of goods.