Analysis And Realization Of The Online Shopping Mall Monitoring And Early Warning System Based On User Behavior Data

With the development of Internet technology,a large amount of data is generated at every moment.The amount of data has become an explosive growth trend,especially in the field of e-commerce.With the increasing number of online purchases,the amount of data recorded by the platform is becoming larger and larger every day.How to make more effective use of the information received and how to ensure the correctness of the information become an urgent problem for the platform.The problem.For example,Amazon,a well-known e-commerce platform in the United States,has the characteristics of personalized and accurate recommendation and quick response compared with other platforms.Because of its unique monitoring and early warning system for user behavior,the information collected about users is fully utilized,which makes personalized recommendation more precise and helps businesses and platform palms.Grasp customers' shopping psychology and open up new sales channels for businesses.With the continuous growth of data mining business related to users' shopping behavior,the demand for visualization of data statistics gradually emerges around data monitoring of e-commerce platform.Based on Jingdong Mall website,APP,Wechat applet,three-terminal user behavior data,as well as business and commodity databases,this paper designs and implements a monitoring and early warning system based on user behavior through spark distributed computing engine,Springmvc,Echarts,jQuery and other front-end frameworks.Mainly meet the recommendation algorithm engineers in training model and prediction results,can quickly statistics and monitor the source data set,so as to judge the quality of the data set,and display some key statistical results,help the leadership of the mall to make decisions conducive to the enterprise.