Research on the Churn of Daily Necessities Users on E-commerce Platform based on Binary Logistic Regression_Vol. 2 No. 3 (JBM 2025)_Journal of Business and Marketing (ISSN: 3005-5717)

Home > Journal of Business and Marketing (ISSN: 3005-5717) > Vol. 2 No. 3 (JBM 2025) >

Research on the Churn of Daily Necessities Users on E-commerce Platform based on Binary Logistic Regression

DOI: https://doi.org/10.62517/jbm.202509307

Author(s)

Jiazhen Tian1, Weipeng Zhang2,*

Affiliation(s)

1School of Business Administration, Ningbo University of Finance and Economics, Ningbo, China 2College of Digital Technology and Engineering, Ningbo University of Finance & Economics, Ningbo, China *Corresponding Author

Abstract

To analyze the influencing factors of churn of daily necessities users, questionnaires were designed and data were collected from four aspects: user behavior, after-sales service, transportation and offline comparison. The binary logistic regression model was used to provide a preliminary churn prediction, and extract the key influencing factors from nine factors: gender, age, educational background, occupation, monthly income, user behavior, after-sales service, transportation problems and offline comparison. After analyzing the model, it can be found four factors, namely educational background, user behavior, after-sales service, transportation and offline comparison have a great influence. The results show that the model is of high accuracy and interpretability in predicting the churn of daily necessities users on e-commerce platforms. This study has certain reference significance for E-commerce platforms to improve user retention rate and improve operation strategy.

Keywords

Daily Necessities; Purchase Intention; Binary Logistic Regression; Customer Churn

References

[1]Xu Lei, Wang Fang. Research on Consumer Purchase Decision-Making Mechanism under Live E-Commerce Mode. Journal of Commercial Economics, 2024, 30(05): 135-139. [2]Li Xiang, Bai Yijie, Shang Meng. Analysis of Factors Affecting the Purchase Intention of New Energy Vehicles. Technology and Market, 2024, 31(08): 189-191. [3]Zhu Lin, Huang Jian. Research on the Influencing Factors of User Stickiness of Social E-Commerce Platforms-Based on Multi-Case Comparative Analysis. E-commerce Letters, 2023, 28(11): 67-72. [4]He Wei, Ma Jing, et al. Early Disease Screening Method Combining Binary Logistic Regression and Feature Engineering. Chinese Journal of Biomedical Engineering, 2024, 35(04): 345-350. [5]Zhang Chen, Liu Xin. Construction and Empirical Analysis of Cross-Border E-Commerce Logistics Efficiency Optimization Model. Logistics Technology and Management, 203, 34(09): 56-60. [6]Wang Ming, Zhao Qiang, Liu Ting. Research on Credit card Default Risk Prediction Model based on Binary Logistic Regression. Financial Technology Research, 2024, 32(06): 78-82. [7]Chen, Yu, Zhang Hua, Li Na. Application Analysis of Binary Logistic Regression in Benign and Malignant Tumor Diagnosis. Journal of Medical Data Analysis, 2023, 29(03): 245-249. [8]Yang Fan, Sun Li. Optimization and Practice of Binary Logistic Regression Model in Credit Risk Assessment. Review of Economy and Management, 2023, 38(12): 189-194. [9]Zhou Tao, Wu Xiao. An Empirical Study on Binary Logistic Regression Algorithm in Users’ Purchase Intention Prediction. Marketing Science, 2024, 31(01): 112-116. [10]Luo Yun, Chen Hui. Research on Precision Marketing Strategy of E-Commerce Platform Based on Big Data. Modern Business, 2024, 33(02): 88-92.