Data processing method and system for searching for value users

Abstract

Provided is a data processing method and system for searching for value users. The method comprises the steps of building a data analysis list in which user names are set as row values and RFM operational indicators are set as column values; according to the RFM operational indicator and stated partition threshold value of each user, dividing data in the data analysis list into principal user data, high-value user data and abnormal user data; sifting and clearing high-value user data and abnormal user data, then saving principal user data; according to a Kmeans clustering method, conducting clustering treatment on the principal user data and obtaining a plurality of clustering clusters; according to AHP (analytic hierarchy process), conducting quantitative value calculation on the center of clustering; according to the quantitative values, classifying the principal user data then obtaining the types of value users. The data processing method and system for searching for value users adopt the RMF operational indicators to take into account the data dimensionality from an overall perspective, and utilize the Kmeans clustering method to make data automatically form clusters, thereby avoiding the problem of a single thinking perspective of dimensionality, and error influences caused by human factors. Hence, the work efficiency is improved.

Description

technical field [0001] The present invention mainly relates to the technical field of data analysis, in particular to a data processing method and system for finding valuable users. Background technique [0002] The traditional method of dividing user value is to divide the data of different dimensions into ranges based on personal subjectiveness, and then combine them to form new dimensions; [0003] The traditional division method has its own limitations: 1. In the process of analysis, when encountering the problem of dividing the data range, it is often screened by one of the dimensions, instead of considering multiple dimensions at the same time, which will affect the accuracy of the conclusion; 2. When the data When the amount of data is large and the data is complex, using traditional division methods will increase the burden on analysts and increase execution costs. Contents of the invention [0004] The technical problem to be solved by the present invention is to...

AI Technical Summary

Problems solved by technology

[0003] The traditional division method has its own limitations: 1. In the process of analysis, when encountering the problem of dividing the data range, it is often screened by one of the dimensions, instead of considering multiple dimensions at the same time, which will affect the accuracy of the conclusion; 2. When the data When the amount of data is large and the data is complex, traditional division methods will increase the burden on analysts and increase execution costs

Images