基于Cox模型的网路视频客户流失研究
Research on Network Video Customer Churn Based on Cox Model
摘要: 网络视频用户数量决定网络视频服务商收益，如何有效地降低客户流失率成为网络视频商家的关注重点。以和鲸社区公开的网络视频客户流失数据为研究样本，运用R语言软件对样本数据进行描述性统计，结合不同的解释变量对生存时间做对比描述分析。然后，对样本数据里的变量建立Cox模型，发现“未订阅电视、没有电影套餐、过去3个月账单平均值(15~30元)、因服务失败而呼叫中心的次数(0次)、过去3个月平均下载量(40 GB以上)、过去3个月平均上传量(3 GB以上)”的客户，流失可能性更低，生存时间更长。
Abstract:
The number of online video users determines the revenue of online video service providers, and how to effectively reduce the customer churn rate has become the focus of online video businesses. Taking the online video customer churn data published by Hejing Community as the research sample, using R software to descriptive statistics of the sample data, and combining different explanatory variables to make a comparative description and analysis of the survival time. Then, build a Cox model for the variables in the sample data, and find that Customers with “no TV subscription, no movie package, average bill in the past 3 months (15~30 yuan), number of calls to the center due to service failure (0), an average download volume of the past 3 months (above 40 GB) and an average upload volume of the past 3 months (above 3 GB)” are less likely to churn and survive longer.
参考文献
|
[1]
|
CNNIC发布第49次《中国互联网络发展状况统计报告》[J]. 新闻潮, 2022(2): 3.
|
|
[2]
|
徐滢, 杏运. 多屏互动专利技术综述[J]. 中国科技信息, 2021(19): 24-25.
|
|
[3]
|
武晓莉. 中国网民规模达10.32亿[N]. 中国消费者报2022-03-03(003).
|
|
[4]
|
Hadden, J., et al. (2005) Computer Assisted Customer Churn Management: State-of-the-Art and Future Trends. Computers and Operations Research, 34, 2902-2917. [Google Scholar] [CrossRef]
|
|
[5]
|
张宇, 张之明. 一种基于C5.0决策树的客户流失预测模型研究[J]. 统计与信息论坛, 2015, 30(1): 89-94.
|
|
[6]
|
胡永培, 张琛. 基于AP聚类与随机森林的客户流失预测研究[J]. 计算机技术与发展, 2021, 31(2): 49-53.
|
|
[7]
|
夏国恩, 唐琪, 张显全. 改进的多层感知机在客户流失预测中的应用[J]. 计算机工程与应用, 2020, 56(14): 257-263.
|
|
[8]
|
Hedge, S. and Mundada, M.R. (2019) Enhanced Deep Feed Forward Neural Network Model for the Customer Attrition Analysis in Banking Sector. International Journal of Intelligent Systems and Applications (IJISA), 11, 10-19. [Google Scholar] [CrossRef]
|
|
[9]
|
Ebrah, K. and Elnasir, S. (2019) Churn Prediction Using Machine Learning and Recommendations Plans for Telecoms. Journal of Computer and Communications, 7, 33-53. [Google Scholar] [CrossRef]
|
|
[10]
|
Walters, S.J. (2012) Analyzing Time to Event Outcomes with a Cox Regression Model. Wiley Interdisciplinary Reviews: Computational Statistics, 4, 310-315. [Google Scholar] [CrossRef]
|
|
[11]
|
Cox, D.R. (1972) Regression Models and Life Tables (with Discussion). Journal of the Royal Statistical Society: Series B, 34, 187-220. [Google Scholar] [CrossRef]
|
|
[12]
|
邓森文, 马溪骏. 基于Cox模型的移动通信行业中低端客户流失预测研究[J]. 合肥工业大学学报(自然科学版), 2010, 33(11): 1698-1701.
|