Empirical Analysis of User Repurchase Behavior Prediction, Channel Attribution and Causal Effect under Multichannel Marketing

Authors

  • Yangshangjia Hu Faculty of Humanities and Arts, Macau University of Science and Technology, Avenida Wai Long, Taipa, Macau, China

DOI:

https://doi.org/10.54097/ey4zb958

Keywords:

E-commerce, Repurchase Prediction, Channel Attribution, Logistics Timeliness, Shapley Value.

Abstract

Against the backdrop of homogeneous e-commerce competition, logistics experience has become a key factor influencing user repurchase, yet its quantitative value and causal effect remain unclear. Based on 115,034 valid user data from a large e-commerce platform, this study constructs an integrated analytical framework of "repurchase prediction-channel attribution- causal verification". Logistic Regression and Random Forest are adopted for repurchase prediction, Shapley value is used to quantify channel contributions, and propensity score matching is employed to verify causal effects. The results show that the Random Forest model achieves the optimal performance (AUC=0.825, F1=0.631); logistics timeliness contributes as high as 77.0% to repurchase, serving as the core driving channel; the core channel combination consisting of the Southeast China Region, credit card payment, and logistics delivery within 3 days can significantly increase the repurchase rate by 3.9 percentage points, with statistically significant results. This study fills the research gap of the disconnect between logistics and multi-channel analysis, providing a scientific basis for enterprise resource allocation.

Downloads

Download data is not yet available.

References

[1] Chen, Y., Zhang, J., 2023. The impact of logistics service quality on e-commerce customer repurchase intention: The mediating role of customer satisfaction. Journal of Business Research. 156, 113289.

[2] Chou, P., Chuang, H. H.-C., Chou, Y.-C., Liang, T.-P., 2021. Predictive analytics for customer repurchase: Interdisciplinary integration of buy till you die modeling and machine learning. European Journal of Operational Research. 294 (3), 1043–1055.

[3] Csoban-Mirka, E., Esqueda-Henríquez, S., Ríos, A., 2024. Predicción del comportamiento de compra online: una aplicación del modelo S-O-R. Retos Revista de Ciencias de la Administración y Economía. 14 (27), 21–33.

[4] Kim, J., Ji, H., Oh, S., Hwang, S., Park, E., del Pobil, A. P., 2021. A deep hybrid learning model for customer repurchase behavior. Journal of Retailing and Consumer Services. 59, 102356.

[5] Li, M., Wang, Y., Zhang, L., 2022. Channel attribution in e-commerce: A comparative study of Shapley value and traditional methods. Electronic Commerce Research and Applications. 56, 101185.

[6] Liang, C., Xingqing, Y., Ma, J., 2021. Can e-commerce improve the profitability of agricultural co-operatives? Transformations in Business & Economics. 20 (2A), 684–700.

[7] Liu, J., Liu, M., Hong, L., Lin, Q., 2025. Improved Shapley Value with Trapezoidal Fuzzy Numbers and Its Application to the E-Commerce Logistics of the Forest Products. Applied Sciences. 15 (1), 123.

[8] Lu, T., Zhang, X., Zhuang, G., 2025. Managing multichannel conflict: the role of interactions enabled by interorganizational information system and public social media. Industrial Marketing Management. 108, 104123.

[9] Obayemi, A., Nguyen, K., 2024. Leveraging Multimodal Shapley Values to Address Multimodal Collapse and Improve Fine-grained E-Commerce Product Classification. Proceedings of the IEEE International Conference on Data Mining (ICDM). pp. 1–6.

[10] Olist., 2018. Olist Brazilian E-Commerce Public Dataset. Kaggle. Retrieved from https://www.kaggle.com/datasets/olistbr/brazilian-ecommerce/data.

[11] Park, E., 2023. CRNet: a multimodal deep convolutional neural network for customer revisit prediction. Journal of Big Data. 10 (1), 15.

[12] Verma, A., Singh, P., Kumar, R., 2025. Enhancing customer repurchase prediction: Integrating classification algorithms with RFM analysis. Journal of Consumer Behaviour. 24 (2), 123–135.

[13] Wang, X., Yao, S., Wang, J., Li, Y., Yu, B., 2022. A Study of Cooperation Between Suppliers and E-Commerce Platforms Based on Biform Game. Journal of Theoretical and Applied Electronic Commerce Research. 17 (4), 1456–1475.

[14] Yılmaz Benk, G., Badur, B., Mardikyan, S., 2022. A New 360° Framework to Predict Customer Lifetime Value for Multi-Category E-Commerce Companies Using a Multi-Output Deep Neural Network and Explainable Artificial Intelligence. Information.

[15] Zhang, H., Hou, Y., He, F.-F., 2022. A Decision Method for Benefit Distribution Mechanism of Shared End Distribution on Shapley Value. Mathematical Problems in Engineering. pp. 1–11.

[16] Zhou, X., Chi, L., Li, J., Xing, L., Yang, L., Wu, J., Meng, H.,2024. A Study on Revenue Distribution of Chinese Agricultural E-Commerce Supply Chain Based on the Modified Shapley Value Method. Sustainability. 16 (20), 9023.

Downloads

Published

17-07-2026

Issue

Section

Articles

How to Cite

Hu, Y. (2026). Empirical Analysis of User Repurchase Behavior Prediction, Channel Attribution and Causal Effect under Multichannel Marketing. Journal of Innovation and Development, 16(1), 83-91. https://doi.org/10.54097/ey4zb958