Proceedings of the 2025 4th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2025)

<Previous Article In Volume
Next Article In Volume>

Research on User Purchase Behavior Prediction Based on Machine Learning Methods

Authors
Shuhan Hu1, Yibo Zhang1, *, Xintong Yu1, Bingfeng Yao2
1Central University of Finance and Economics, Beijing, 101319, China
2Minzu University of China, Beijing, 100081, China
*Corresponding author. Email: 2024311325@emai.cufe.edu.cn
Corresponding Author
Yibo Zhang
Available Online 20 February 2026.
DOI
10.2991/978-94-6463-992-6_33How to use a DOI?
Keywords
Purchase Behavior Prediction; Machine Learning; LightGBM; Multi-window Feature Engineering; E-commerce
Abstract

To address the issues of limited dimensionality in implicit feedback data and dynamic changes in user interests in predicting e-commerce user purchase behavior in the digital economy era, this study is based on the Retailrocket dataset, retaining 6,610 valid samples after preprocessing. By setting long (14-day), medium (7-day), and short (3-day) time sliding windows, 84 features are constructed from five dimensions including user, product, and category. After comparing XGBoost, LightGBM, and CatBoost, LightGBM is selected as the base model, and a Bagging fusion strategy with parameter perturbation is proposed. The study incorporates game theory principles to model the strategic interactions between platforms, merchants, and consumers in digital marketplaces. Experiments show that the F1-score of the fusion model reaches 0.6107, an improvement of 7.7% compared to the single LightGBM, providing support for e-commerce precision marketing and digital economy platform optimization strategies.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 4th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2025)
Series
Advances in Economics, Business and Management Research
Publication Date
20 February 2026
ISBN
978-94-6463-992-6
ISSN
2352-5428
DOI
10.2991/978-94-6463-992-6_33How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Shuhan Hu
AU  - Yibo Zhang
AU  - Xintong Yu
AU  - Bingfeng Yao
PY  - 2026
DA  - 2026/02/20
TI  - Research on User Purchase Behavior Prediction Based on Machine Learning Methods
BT  - Proceedings of the 2025 4th International Conference on Mathematical Statistics and Economic Analysis (MSEA 2025)
PB  - Atlantis Press
SP  - 361
EP  - 368
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-992-6_33
DO  - 10.2991/978-94-6463-992-6_33
ID  - Hu2026
ER  -