Customer churn prediction based on the integration of meta-learning network of the forest

LI Longge; ZHENG Kengcheng

doi:10.11959/j.issn.1000-0801.2024159

您当前的位置：

首页 >

文章列表页 >

Customer churn prediction based on the integration of meta-learning network of the forest

Engineering and Application | 更新时间：2024-12-02

- Customer churn prediction based on the integration of meta-learning network of the forest
- Telecommunications Science Vol. 40, Issue 10, Pages: 163-172(2024)
- 作者机构：
  
  1.中国通信建设集团设计院有限公司数字化咨询中心，河南郑州 450000
  2.中南财经政法大学，湖北武汉 430073
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2024159
  CLC： TP183
- Received：14 January 2024，
  
  Revised：20 April 2024，
  
  Published：20 October 2024
- 稿件说明：
移动端阅览
李龙戈,郑铿城.基于集成森林元学习网络的客户流失预测[J].电信科学,2024,40(10):163-172.

LI Longge,ZHENG Kengcheng.Customer churn prediction based on the integration of meta-learning network of the forest[J].Telecommunications Science,2024,40(10):163-172.
李龙戈,郑铿城.基于集成森林元学习网络的客户流失预测[J].电信科学,2024,40(10):163-172. DOI： 10.11959/j.issn.1000-0801.2024159.

LI Longge,ZHENG Kengcheng.Customer churn prediction based on the integration of meta-learning network of the forest[J].Telecommunications Science,2024,40(10):163-172. DOI： 10.11959/j.issn.1000-0801.2024159.

摘要

为解决树模型在客户流失预测任务中较难捕捉时序特征的问题，提出了基于集成森林元学习网络（ensemble forest meta-learning network，EFML）的流失预测方法。首先通过分组等策略进行数据提质，并结合下采样技术解决样本类别不平衡问题。然后，基于EFML的语义图构造器构建用户时序特征的语义向量，以描绘用户细粒度行为，形成语义图并显式融合。最后，训练多个基础树模型作为元学习器-多层感知机（multilayer perceptron，MLP）的输入，生成综合的流失预测结果。实验证明，EFML能充分挖掘客户历史行为差异，捕获和学习基础树模型间的互补关系，相对于随机森林（random forest，RF），其AUC提升2.7%，AP提升3.7%，预测精度提升显著。该框架结合树模型和微观特征，具备卓越的解释性，为运营商实现更精细的用户化管理提供新视角。

Abstract

To address the challenge of capturing temporal features in customer churn prediction tasks by tree models

a churn prediction method based on ensemble forest meta-learning network (EFML) was proposed. Firstly

data quality was improved through grouping strategies and class imbalance issues were addressed with undersampling techniques. Secondly

semantic vectors of user temporal features were constructed using EFML’s semantic graph constructor to depict fine-grained user behavior

forming a semantic graph and explicitly integrating it. Finally

multiple base tree models were trained as meta-learners

with the inputs being multilayer perceptron (MLP) to generate comprehensive churn prediction results. Experimental results demonstrate that EFML can effectively exploit differences in customer historical behaviors

capture and learn complementary relationships between base tree models. Compared to random forest (RF)

EFML shows a 2.7% increase in AUC

a 3.7% increase in AP

and a significant improvement in prediction accuracy. This framework

combining tree models and micro-level features

possesses excellent interpretability

providing a new perspective for operators to achieve more refined user-centric management.

关键词

Keywords

references

阿克弘 , 胡晓东 . 基于GAN数据重构的电信用户流失预测方法 [J ] . 电信科学 , 2023 , 39 ( 3 ): 135 - 142 .

A K H , HU X D . GAN data reconstruction based prediction method of telecom subscriber loss [J ] . Telecommunications Science , 2023 , 39 ( 3 ): 135 - 142 .

黄子璇 , 夏壬焕 , 张雄涛 . 基于注意力机制和图卷积的电信客户流失预测 [J ] . 计算机工程与设计 , 2023 , 44 ( 6 ): 1685 - 1691 .

HUANG Z X , XIA R H , ZHANG X T . Prediction of telecom customer churn based on attention mechanism and graph convolution [J ] . Computer Engineering and Design , 2023 , 44 ( 6 ): 1685 - 1691 .

钟保权 . 基于图学习的电信用户流失预测算法 [D ] . 杭州 : 浙江大学 , 2021 .

ZHONG B Q . Graph Learning Algorithm for Tele-com User Churn Prediction [D ] . Hangzhou : Zhejiang University , 2021 .

ZHANG T Y , MORO S , RAMOS R F . A data-driven approach to improve customer churn prediction based on telecom customer segmentation [J ] . Future Internet , 2022 , 14 ( 3 ): 94 .

MARTINS H . Predicting user churn on streaming services using recurrent neural networks [D ] . KTH Royal Institute of Technology , 2017 .

DE CAIGNY A , COUSSEMENT K , DE BOCK K W . A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees [J ] . European Journal of Operational Research , 2018 , 269 ( 2 ): 760 - 772 .

ULLAH I , RAZA B , MALIK A K , et al . A churn prediction model using random forest: analysis of machine learning techniques for churn prediction and factor identification in telecom sector [J ] . IEEE Access , 2019 , 7 : 60134 - 60149 .

HÖPPNER S , STRIPLING E , BAESENS B , et al . Profit driven decision trees for churn prediction [J ] . European Journal of Operational Research , 2020 , 284 ( 3 ): 920 - 933 .

AHMAD A K , JAFAR A , ALJOUMAA K . Customer churn prediction in telecom using machine learning in big data platform [J ] . Journal of Big Data , 2019 , 6 ( 1 ): 28 .

MENG Q , KE G L , WANG T F , et al . A communication-efficient parallel algorithm for decision tree [EB ] . 2016 : 1611 .01276.

KE G , MENG Q , FINLEY T , et al . Lightgbm: a highly efficient gradient boosting decision tree [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . Long Beach : ACM Press , 2017 . 3149 - 3157 .

魏志强 , 张浩 , 陈龙 . 一种采用SmoteTomek和LightGBM算法的Web异常检测模型 [J ] . 小型微型计算机系统 , 2020 , 41 ( 3 ): 587 - 592 .

WEI Z Q , ZHANG H , CHEN L . Web anomaly detection model using SmoteTomek and LightGBM algorithm [J ] . Journal of Chinese Computer Systems , 2020 , 41 ( 3 ): 587 - 592 .

SHI H . Best-first decision tree learning [D ] . Hamilton : The University of Waikato , 2007 .

SUN X L , LIU M X , SIMA Z Q . A novel cryptocurrency price trend forecasting model based on LightGBM [J ] . Finance Research Letters , 2020 , 32 : 101084 .

MIRONOV S V , SIDOROV S P . Duality gap estimates for weak Chebyshev greedy algorithms in Banach spaces [J ] . Computational Mathematics and Mathematical Physics , 2019 , 59 ( 6 ): 904 - 914 .

CHEN T Q , GUESTRIN C . XGBoost: A scalable treeboosting system [C ] // Proceedings of the 22nd ACMSIGKDD International Conference on KnowledgeDiscovery and Data Mining . San Francisco : ACM Press , 2016 . 785 - 794 .

ZHENG H , LI H B , LU X J , et al . A multiple kernel learning approach for air quality prediction [J ] . Advances in Meteorology , 2018 : 3506394 .

周艳聪 , 郝园媛 . 基于机器学习的运营商客户行为分析 [J ] . 科学技术与工程 , 2022 , 22 ( 2 ): 585 - 592 .

ZHOU Y C , HAO Y Y . Research of operator customer behavior analysis based on machine learning algorithm [J ] . Science Technology and Engineering , 2022 , 22 ( 2 ): 585 - 592 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰