Application of the RFA-XGBoost model in predicting potential complaint users in mobile network

ZHANG Peng; GAO Yuan

doi:10.11959/j.issn.1000-0801.2025036

您当前的位置：

首页 >

文章列表页 >

Application of the RFA-XGBoost model in predicting potential complaint users in mobile network

Engineering and Application | 更新时间：2025-04-24

- Application of the RFA-XGBoost model in predicting potential complaint users in mobile network
- Telecommunications Science Vol. 41, Issue 3, Pages: 167-178(2025)
- 作者机构：
  
  中国移动通信集团设计院有限公司湖北分公司，湖北武汉 430021
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025036
  CLC： TP391
- Received：08 November 2024，
  
  Revised：2025-02-11，
  
  Published：20 March 2025
- 稿件说明：
移动端阅览
张鹏,高源.RFA-XGBoost模型在移动网络潜在投诉用户预测中的应用[J].电信科学,2025,41(03):167-178.

ZHANG Peng,GAO Yuan.Application of the RFA-XGBoost model in predicting potential complaint users in mobile network[J].Telecommunications Science,2025,41(03):167-178.
张鹏,高源.RFA-XGBoost模型在移动网络潜在投诉用户预测中的应用[J].电信科学,2025,41(03):167-178. DOI： 10.11959/j.issn.1000-0801.2025036.

ZHANG Peng,GAO Yuan.Application of the RFA-XGBoost model in predicting potential complaint users in mobile network[J].Telecommunications Science,2025,41(03):167-178. DOI： 10.11959/j.issn.1000-0801.2025036.

摘要

为了提前预测并减少移动网络用户投诉事件的发生，深入研究了多维数据分析在移动网络潜在投诉用户预测中的应用。采集移动网络用户广泛的业务域和运营域指标作为输入特征数据，成功构建了基于极限梯度提升（extreme gradient boosting，XGBoost）算法的潜在投诉用户预测模型，该模型在测试集上平均预测准确率达96.35%。同时，提出了迭代特征增强XGBoost（recursive feature augmented XGBoost，RFA-XGBoost）预测模型用于潜在投诉用户预测，即通过不断迭代将前一轮XGBoost模型的预测输出作为新的特征添加到特征集中，并重新训练新一轮的XGBoost模型，优化后的平均预测准确率可提升至98.89%。所提研究成果对于移动网络运营商而言，意味着能够更早地识别并介入潜在投诉情况，从而有效预防投诉事件的发生，进一步提升用户满意度和服务质量，具有重要的实践意义和商业价值。

Abstract

In order to predict and reduce the occurrence of complaints of mobile network users in advance

the application of multidimensional data analysis in the prediction of potential complaints of mobile network users was deeply studied. By collecting a wide range of business domain and operation domain indicators of mobile network users as input feature data

a potential complaint user prediction model based on extreme gradient boosting (XGBoost) was successfully constructed

which had an average prediction accuracy of 96.35% on the test set. At the same time

the recursive feature augmented XGBoost (RFA-XGBoost) prediction model was proposed for the prediction of potential complaint users. By iteratively adding the predicted output of the previous round of XGBoost model to the feature set as a new feature and retraining the new round of XGBoost model

the average prediction accuracy after optimization could be improved to 98.89%. For mobile network operators

the research results mean that they can identify and intervene in potential complaints earlier

so as to effectively prevent the occurrence of complaints and further improve user satisfaction and service quality

which has important practical significance and commercial value.

关键词

Keywords

references

胡怡 . 消费保平台三大运营商投诉数据简报 [J ] . 消费电子 , 2024 ( 2 ): 17 - 20 .

HU Y . Complaint data briefing for the three major operators of consumer insurance platforms [J ] . Consumer Electronics , 2024 ( 2 ): 17 - 20 .

俞涛 , 郝洁 , 张小晖 . 运营商用户投诉预判模型研究 [J ] . 移动信息 , 2023 ( 2 ): 208 - 210 .

YU T , HAO J , ZHANG X H . Research on the prediction model of operator customer complaints [J ] . Mobile Information , 2023 ( 2 ): 208 - 210 .

龙克树 , 邓娟 , 刘晓斌 . 基于机器学习算法的运营商用户流失预判及应对策略研究 [J ] . 信息记录材料 , 2020 , 21 ( 5 ): 202 - 205 .

LONG K S , DENG J , LIU X B . Research on predicting and coping strategies of operator’s user loss based on machine learning algorithm [J ] . Information Recording Materials , 2020 , 21 ( 5 ): 202 - 205 .

刘平 . 移动网智能化网络投诉处理系统研究 [J ] . 通讯世界 , 2021 ( 7 ): 21 - 22 .

LIU P . Research on intelligent network complaint handling system of mobile network [J ] . Telecom World , 2021 ( 7 ): 21 - 22 .

吴亚楠 . 客户无线网络投诉的预防措施研究 [J ] . 无线互联科技 , 2020 , 17 ( 24 ): 15 - 16 .

WU Y N . Research on preventive measure of customer complaints in wireless network [J ] . Wireless Internet Technology , 2020 , 17 ( 24 ): 15 - 16 .

万仁辉 , 王洁 , 戴鹏程 , 等 . 基于机器学习的网络投诉预测分析 [J ] . 电信工程技术与标准化 , 2020 , 33 ( 8 ): 45 - 50 .

WAN R H , WANG J , DAI P C , et al . Prediction and analysis of network complaints based on machine learning [J ] . Telecom Engineering Technics and Standardization , 2020 , 33 ( 8 ): 45 - 50 .

陈秀敏 , 许向东 , 黄毅华 , 等 . 基于数据挖掘的4G用户投诉预测 [J ] . 移动通信 , 2017 , 41 ( 21 ): 30 - 36 .

CHEN X M , XU X D , HUANG Y H , et al . Prediction of 4G user complaints based on data mining [J ] . Mobile Communications , 2017 , 41 ( 21 ): 30 - 36 .

宗宇雷 , 梁童 , 吴伟嘉 , 等 . 一种基于XGBoost算法的用户投诉预测方法 [J ] . 电信工程技术与标准化 , 2023 , 36 ( 11 ): 7 - 12 .

ZONG Y L , LIANG T , WU W J , et al . A user complaint prediction method based on XGBoost algorithm [J ] . Telecom Engineering Technics and Standardization , 2023 , 36 ( 11 ): 7 - 12 .

CHEN T Q , GUESTRIN C . XGBoost: a scalable tree boosting system [EB ] . 2016 , arXiv: 1603.02754 .

王可争 , 潘丹 . 一种利用神经网络预测用户投诉的方法 [J ] . 通信世界 , 2021 ( 12 ): 45 - 48 .

WANG K Z , PAN D . A method for predicting user complaints by using neural network [J ] . Communications World , 2021 ( 12 ): 45 - 48 .

马洁 . 基于数据挖掘与业务感知的投诉预测模型研究 [J ] . 电信工程技术与标准化 , 2022 , 35 ( S1 ): 115 - 121 .

MA J . Research on complaint prediction model based on data mining and business awareness [J ] . Telecom Engineering Technics and Standardization , 2022 , 35 ( S1 ): 115 - 121 .

周文杰 , 严建峰 , 杨璐 . 基于深度学习的用户投诉预测模型研究 [J ] . 计算机应用研究 , 2017 , 34 ( 5 ): 1428 - 1432 .

ZHOU W J , YAN J F , YANG L . Research on prediction model of complaint based on deep learning [J ] . Application Research of Computers , 2017 , 34 ( 5 ): 1428 - 1432 .

HINTON G E . Deep belief networks [J ] . Scholarpedia , 2009 , 4 ( 5 ): 5947 .

KE G L , 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(NIPS'17) . California : Curran Associates Inc , 2017 : 3149 - 3157 .

BEJA-BATTAIS P . Overview of AdaBoost: Reconciling its views to better understand its dynamics [EB ] . arXiv preprint , 2023 , arXiv:2310. 18323 .

FRIEDMAN J H . Greedy function approximation: A gradient boosting machine [J ] . The Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

Views

661

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on customer escalated complaints prediction based on LLM-RFE-XGBoost approach

Smart CAPEX wireless network planning method integrating multi-source data and machine learning

Research on telecom industry customer churn prediction based on explainable machine learning models

A single flow detection enabled method for DDoS attacks in IoT based on traffic feature reconstruction and mapping

Research and application of adaptive algorithm for 5G voice quality evaluation

Related Author

Qiao Yaqian

Wang Qian

Liu Fang

Xu Yu

Jiang Jun

Dou Zhongzhao

Zhou Hong

Yang Mingshuai

Related Institution

China Mobile Online Service Co., Ltd., AI Capability Center

China Mobile Online Service Co., Ltd., Shandong Branch

China Telecom Global Limited

College of Statistics and Data Science, Xinjiang University of Finance and Economics

School of Safety Science and Engineering, Civil Aviation University of China

⁰