A Novel Digital Coupon Use Prediction Model Based on XGBoost

DOI

10.2991/icmesd-18.2018.134How to use a DOI?

Keywords

Digital coupon, Extreme Gradient Boosting, Feature engineering, Prediction.

Abstract

It was found that traditional predicting models of coupons could only process small-scale data, thus were unable to precisely predict whether consumers would use new digital coupons in the future. By introducing the feature engineering and the machine learning algorithm of Extreme Gradient Boosting (XGBoost), a novel Digital Coupon Use Prediction Model (DCUPM) was established to deal with vast amount of historical data and to provide high-precision prediction of the future digital coupons use of consumers. In this paper, an example of this DCUPM was then presented and analyzed based on the data provided by Alibaba Cloud. The result shows the Area under the Curve (AUC) is calculated to be 0.896, which demonstrates the reliability of the proposed DCUPM. And features with higher scores can be used to achieve targeted delivery of digital coupons for businesses.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lu Song
AU  - Wen-Sheng Yang
PY  - 2018/05
DA  - 2018/05
TI  - A Novel Digital Coupon Use Prediction Model Based on XGBoost
BT  - Proceedings of the 4th Annual International Conference on Management, Economics and Social Development (ICMESD 2018)
PB  - Atlantis Press
SP  - 775
EP  - 782
SN  - 2352-5428
UR  - https://doi.org/10.2991/icmesd-18.2018.134
DO  - 10.2991/icmesd-18.2018.134
ID  - Song2018/05
ER  -