RFA-XGBoost模型在移动网络潜在投诉用户预测中的应用  

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

作　　者：张鹏 高源 ZHANG Peng;GAO Yuan(China Mobile Group Design Institute Co.,Ltd.,Hubei Branch,Wuhan 430021,China)

机构地区：[1]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

出　　处：《电信科学》2025年第3期167-178,共12页Telecommunications Science

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,RFAXGBoost)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。In order to predict and reduce the occurrence of complaints of mobile network users in advance,the appli cation 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 re cursive 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 in tervene 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：潜在投诉用户预测 机器学习 XGBoost 数据挖掘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]