摘要
为解决预测潜在换机用户的低效率与实际应用问题,设计并搭建基于大数据平台的换机预测系统。该系统首先采集通信网络各接口的数据并收集外部数据,通过解析处理平台对网络接口数据进行分发、解码、合成、关联等处理,对外部数据进行ETL处理;然后将处理后的数据存入HDFS中,在大数据平台上应用Spark组件建立基于逻辑回归的换机预测模型,输出潜在换机用户;最后选取了某西部城市部分用户数据进行系统测试。所得结果表明,该换机预测系统的预测准确率为71%,可以较好地识别出潜在换机用户,为运营商及手机制造商的精准营销提供可靠支撑。
In order to solve the low efficiency and practical application of predicting the potential phone replacement user,this paper designed and built a phone replacement prediction system based on big data platform. This system firstly captured signaling data from multiple network interface and collected external data. Through the parse platform,the data from network interface would be distributed,decoded,synthesized and correlated,and the external data would be processed by ETL tools,and then storing processed data into HDFS. Further,this paper established a phone replacement prediction model,which based on logistic regression,using spark components in the big data platform and output the potential phone replacement users. Finally,this paper chose part of the western city's user data for system testing. The result shows that the prediction accuracy of the phone replacement prediction system is up to 71%. It can preferably recognize potential phone replacement users,and provide reliable support for the precise marketing of operators and mobile phone manufacturers.
引文
[1]Zhao Shuang,Ma Jing.Research on precision marketing data source system based on big data[J].International Journal of Advanced Media&Communication,2017,7(2):93-100.
[2]You Zhen,Si Y W,Zhang Defu,et al.A decision-making framework for precision marketing[J].Expert Systems with Applications,2015,42(7):3357-3367.
[3]刘力凯,王国胤,邓维斌.优势关系粗糙集的移动用户换机预测方法[J].小型微型计算机系统,2015,36(8):1789-1794.(Liu Likai,Wang Guoyin,Deng Weibin.Prediction of mobile users for updating terminal method based on dominance-based rough set approach[J].Journal of Chinese Mini-Micro Computer Systems,2015,36(8):1789-1794.)
[4]刘畅.基于Cox回归模型的用户终端换机研究[J].电子科学技术,2016,3(4):418-421.(Liu Chang.Customers’cell phone replacement study:based on cox regression model[J].Electronic Science&Technology,2016,3(4):418-421.)
[5]熊冰妍,王国胤,邓维斌.分级式代价敏感决策树及其在手机换机预测中的应用[J].山东大学学报:工学版,2015,45(5):36-42.(Xiong Bingyan,Wang Guoyin,Deng Weibin.Hierarchical cost sensitive decision tree and its application in the prediction of the mobile phone replacement[J].Journal of Shandong University:Engineering Edition,2015,45(5):36-42.)
[6]Yang Dun,Wu Zhi’ang,Wang Xiaopeng,et al.Predicting replacement of smartphones with mobile app usage[C]//Proc of International Conference on Web Information Systems Engineering.[S.l.]:Springer International Publishing,2016:343-351.
[7]Ghazi M R,Gangodkar D.Hadoop,MapReduce and HDFS:a developers perspective[J].Procedia Computer Science,2015,48(12):45-50.
[8]Edition S.Applied logistic regression analysis[J].Technometrics,1996,38(2):184-186.
[9]Wallenstein S,Hodge S E,Weston A.Logistic regression model for analyzing extended haplotype data[J].Genetic Epidemiology,2015,15(2):173-181.
[10]Zhang Zhongheng.Model building strategy for logistic regression:purposeful selection[J].Annals of Translational Medicine,2016,4(6):111.
[11]Zhang Shangli,Zhang Lili,Qiu Kuanmin,et al.Variable selection in logistic regression model[J].Chinese Journal of Electronics,2015,24(4):813-817.
[12]Olive D J.Linear regression analysis[J].Technometrics,2003,45(4):362-363.
[13]Abuella M,Chowdhury B.Solar power probabilistic forecasting by using multiple linear regression analysis[C]//Proc of SoutheastCon.Piscataway,NJ:IEEE Press,2015:1-5.