Education, Science, Technology, Innovation and Life
Open Access
Sign In

MDBIF: A Multi-Dimensional Feature and Boosting Integration Framework for O2O Coupon Redemption Prediction

Download as PDF

DOI: 10.23977/jeis.2025.100209 | Downloads: 0 | Views: 58

Author(s)

Jiaqi Xu 1, Zichen Liang 2

Affiliation(s)

1 Lanzhou Zhicheng Academy, Lanzhou, Gansu, China
2 The High School Attached to Northwest Normal University, Lanzhou, Gansu, China

Corresponding Author

Jiaqi Xu

ABSTRACT

The low redemption rate of coupons in Online-to-Offline (O2O) platforms poses a key challenge for marketing efficiency. To address this, we propose a Multi-Dimensional Feature and Boosting Integration Framework (MDBIF) that captures user, merchant, coupon, and interaction behaviors across seven feature groups with 26 new features. Using mutual information for feature selection and comparing XGBoost, LightGBM, and CatBoost, our framework enhances prediction robustness via data fusion and tuning. Experiments on a real-world Alibaba Tmall dataset (1.75M records) show that LightGBM achieves the best performance (AUC 0.9961, accuracy 0.9815). Key features such as user-specific coupon receipt frequency and merchant distance prove critical. Based on this, we offer actionable targeting strategies to improve O2O coupon effectiveness. Our approach provides a scalable solution for precision marketing in O2O ecosystems.

KEYWORDS

O2O Coupons, Machine Learning, Feature Engineering, Model Integration, Targeted Delivery

CITE THIS PAPER

Jiaqi Xu, Zichen Liang, MDBIF: A Multi-Dimensional Feature and Boosting Integration Framework for O2O Coupon Redemption Prediction. Journal of Electronics and Information Science (2025) Vol. 10: 74-81. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2025.100209.

REFERENCES

[1] Huang, B., Hu, X., & Zhai, J. (2023). Research on O2O coupon distribution strategy based on machine learning. In Proceedings of the 18th Annual Conference of the Chinese Academy of Management Science and the 10th Anniversary Forum of the Belt and Road Initiative (pp. 511–521). China University of Mining and Technology; Hunan University. https://doi.org/10.26914/c.cnkihy.2023.029347
[2] Zhang, X., Qiu, J., & Li, B. (2024). Precise Issuance of Meituan Merchants' Coupons with Machine Learning. In Proceedings of the International Conference on Machine Learning, Pattern Recognition and Automation Engineering (pp. 71-75).
[3] Mei, H., & Li, X. (2019). Research on e-commerce coupon user behavior prediction technology based on decision tree algorithm. International Core Journal of Engineering, 5(9), 48-58.
[4] Song, X. (2021). Research and application of O2O coupon usage prediction based on XGBoost (Master's thesis). Southwest Jiaotong University. https://doi.org/10.27414/d.cnki.gxnju.2021.002056
[5] Weihan Yang,Zijie Zhang,Runze Liu & Jinjiang Liu.(2023).Forecast of O2O Coupon Consumption Based on XGBoost Model.Academic Journal of Computing & Information Science,6(8)
[6] Qiongyu, S. (2020). Prediction of o2o coupon usage based on xgboost model. In Proceedings of the 2020 11th International Conference on E-business, Management and Economics (pp. 33-36).
[7] Wang, L. (2023). Research on O2O coupon prediction based on data mining (Master's thesis). Dalian University of Technology. https://doi.org/10.26991/d.cnki.gdllu.2023.004622 
[8] Meijuan, S., & Kaili, Y. (2024, December). Research on O2O Coupon Usage Prediction Based on Machine Learning. In 2024 IEEE 2nd International Conference on Electrical, Automation and Computer Engineering (ICEACE) (pp. 1637-1641). IEEE.

Downloads: 12880
Visits: 521145

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.