Predictive Model of the Revisit Behavior of Cloud Service Site Users

doi:10.11871/jfdc.issn.2096-742X.2022.03.009

Abstract

Abstract:

[Objective] In order to know users' interests and needs, and improve the effectiveness of online recommendation and website operation, it is of great value to predict user behavior based on user browsing and operation behavior data. [Methods] Through data collection, feature selection, data mining, and analysis of the user behavior of the China Science and Technology Cloud (CSTCloud) website, the user revisit behavior can be predictable. The Logical Regression(LR) model and XGBoost model are trained respectively to predict the user revisit behavior, and multi-dimensional numerical evaluation is performed through real user behavior data. [Results] The results show that the LR model has better fitness and accuracy, which is different from the previous opinion that the XGBoost model is better. Identifying the characteristics of the behavioral data structure is the main reason. [Conclusions] The research in this paper is conducive to predict revisit behavior of CSTcloud website users, which enables personalized operation decisions for potential valuable users and improves user experience.

Key words: user behavior, prediction, machine learning, logistic regression, decision tree

WEI Ting,ZHANG Honghai,LIN Xiaoli,ZHANG Leilei,WANG Yan,JIA Jinfeng. Predictive Model of the Revisit Behavior of Cloud Service Site Users[J]. Frontiers of Data and Computing, 2022, 4(3): 124-130, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2022.03.009.

Figures/Tables 5

Table 1

Fig.1

Fig.2

Fig.3

Table 2

References 14

[1]	卓灵, 孙昕. 一种基于改进RFM模型的数字集群用户分类方法[J]. 计算机应用研究, 2020(9): 2822-2826.
[2]	明勇, 张文斌, 陈小军. 基于RFM购买树的客户分群[J]. 深圳大学学报理工版, 2017(3): 306-312.
[3]	Silahtaroglu G, Donertasli H. Analysis and prediction of Ε-customers behavior by mining clickstream data[C]. 2015 IEEE International Conference on Big Data. 2015: 1466-1472.
[4]	Qiu J, Lin Z, Li Y. Predicting customer purchase behavior in the e-commerce context[J]. Electronic Commerce Res-earch, 2015, 15(4):427-452.
[5]	周成骥. 基于机器学习的商品购买行为预测模型设计[D]. 广州大学, 2018.
[6]	顾海斌. 基于大规模电商数据的用户消费行为分析方法研究[D]. 吉林大学, 2016.
[7]	李美其, 齐佳音. 基于购买行为及评论行为的用户购买预测研究[J]. 北京邮电大学学报(社会科学版), 2016, 18(4):18-25.
[8]	杜世民. 基于分类模型的电商用户复购行为预测研究[D]. 阿里巴巴商学院, 2019.
[9]	洪硕. 旅游移动电商环境下的游客购买决策影响因素研究[D]. 广西师范大学, 2018.
[10]	罗胜. 电子商务环境下化妆品消费者冲动性购买行为研究[D]. 华南理工大学, 2018.
[11]	李日旭. 网购生鲜农产品中感知风险对购买意愿的影响研究[D]. 哈尔滨工业大学, 2017.
[12]	张春桃. 顾客感知价值对消费者网购行为影响研究[J]. 商, 2016(01):281.
[13]	曾宪宇. 电商用户消费行为预测与心理建模方法研究[D]. 中国科学技术大学, 2017.
[14]	危婷, 张宏海, 蔺小丽, 张蕾蕾, 王妍, 贾金峰, 吴笛. 中国科技云门户用户忠诚度的研究[J]. 数据与计算发展前沿, 2020, 2(6):74-81.

数据分类	数据举例	数据来源
总体浏览数据	用户总访问量;访问用户数访问页面数	用户行为分析系统日志; 服务器日志
用户属性数据	登录账号;单位;浏览器;操作系统;终端;国家;城市
用户个性化访问数据	访问频率;访问时间间隔;访问次数;平均停留时间;平均访问页面数
访问深度数据	跳出率;访问路径

指标	XGBoost	LR
accuracy	0.940810	0.950156
precision	0.428571	0.750000
recall	0.352941	0.166667
F1-score	0.387097	0.272727
AUC	0.663313	0.841951

[1]	ZHAO Zhongbin,CAI Manchun,LU Tianliang. Network Malicious Traffic Detection Incorporating Multi-Head Attention Mechanism [J]. Frontiers of Data and Computing, 2022, 4(5): 60-67.
[2]	SUN Yongqian,ZHANG Ruru,LIN Zihan,ZHANG Shenglin,TAN Zhiyuan,ZHANG Yuzhi. Evaluation of KPI Anomaly Detection Methods [J]. Frontiers of Data and Computing, 2022, 4(3): 46-65.
[3]	LIU Xiaoyan,WANG Jue,YAO Tiechui,CHI Xuebin,WANG Xiaoguang,LI Kai. A Distributed Photovoltaic Power Prediction System Based on Time Series Data Processing [J]. Frontiers of Data and Computing, 2021, 3(4): 140-148.
[4]	ZHANG Yining,HE Hongbo,WANG Runqiang. A Survey on Popular Digital Audio Prediction Techniques [J]. Frontiers of Data and Computing, 2021, 3(4): 81-92.
[5]	PU Jiansu,ZHU Zhengguo,SHAO Hui,GAO Boyang,ZHU Yanlin,YAN Zongkai,XIANG Yong. Screening and Predication of Solid Electrolyte Based on Visualization [J]. Frontiers of Data and Computing, 2021, 3(4): 18-29.
[6]	ZHANG Shuying,HAN Xinyin,HE Xiaoyu,YUAN Danyang,LUAN Haijing,LI Ruilin,HE Jiayin,NIU Beifang. Review of Genomic Microsatellite Status Detection Based on Machine Learning [J]. Frontiers of Data and Computing, 2021, 3(3): 126-135.
[7]	XIAO Jianping,LONG Chun,ZHAO Jing,WEI Jinxia,HU Anlei,DU Guanyao. A Survey on Network Intrusion Detection Based on Deep Learning [J]. Frontiers of Data and Computing, 2021, 3(3): 59-74.
[8]	GUO Jialong,WANG Zongguo,WANG Yangang,ZHAO Xushan,SU Yanjing,LIU Zhiwei. A Review of Material Research and Development Methods Based on Computer Technology [J]. Frontiers of Data and Computing, 2021, 3(2): 120-132.
[9]	LIU Chunyu,SHI Zhuomin,YU Jianjun. Tree Model Based Prediction of Financial Reimbursement Approval [J]. Frontiers of Data and Computing, 2021, 3(2): 60-67.
[10]	Ren Huiying,Wang Jing,Wang Yangang. Turbulence Modeling Based on AutoML [J]. Frontiers of Data and Computing, 2020, 2(4): 121-131.
[11]	Liu Kunpeng,Zhao Xiaosa,Hu Yirui,Fu Yanjie. Modeling the Effects of Individual and Group Heterogeneity on Multi-Aspect Rating Behavior [J]. Frontiers of Data and Computing, 2020, 2(2): 59-77.
[12]	Li Zixin,Zhang Neng,Xiong Bin,Hu Yunfeng,Zhao Xinpeng,Huang Haiyou. Materials Science Database in Material Research and Development: Recent Applications and Prospects [J]. Frontiers of Data and Computing, 2020, 2(2): 78-90.
[13]	Haitao Zhao, Jiachang Sun, Leisheng Li, Wenhao Yang, Hui Zhao, Huiyuan Li. Research on HPL Parallel Computing Model for a Class of Complex Heterogeneous Supercomputer System [J]. Frontiers of Data and Computing, 2020, 2(1): 85-92.
[14]	Qian Xu,Tian Ziqi. The Application of Materials Genome Approach in Materials Design [J]. Frontiers of Data and Computing, 2020, 2(1): 128-141.
[15]	Li Xiaohan,Chen Wenguang. COS: Measuring the Efficiency of Distributed Big Data Processing System [J]. Frontiers of Data and Computing, 2020, 2(1): 93-104.