User income prediction method and system

Abstract

The invention discloses a method and system for predicting the income of a user, and the method comprises the steps: building a prediction model which comprises an attribute type for predicting the income of the user and a plurality of income levels; collecting each piece of attribute information of a user to be predicted corresponding to the attribute category in the prediction model; and according to the prediction model and the attribute information of the to-be-predicted user, calculating a probability value of the to-be-predicted user falling into each income level in the prediction model, and according to the income level corresponding to the calculated highest probability value, predicting an income condition of the to-be-predicted user. The income condition of the user can be accurately predicted, and the implementation cost is low.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for predicting user income and a system for predicting user income. Background technique [0002] At present, the mining method of high-income customers mainly focuses on developed regions / key industries, and uses manual methods to conduct extensive surveys and mining of people in developed regions and key industries. The disadvantages of the above method are: first, the target is poorly targeted, and it is impossible to locate precise groups of people; second, the labor cost is too high, requiring manual field work; third, the survey results are inaccurate, the quality of researchers is uneven, and customers do not cooperate, etc. , leading to poor reliability of the research results. [0003] Therefore, it is particularly necessary to propose a scheme that can accurately predict user income while saving prediction costs. Contents of the invention [0004] The pre...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and system for predicting user income, so as to solve the current problems of low pertinence in predicting user income, inaccurate prediction results, and high cost.

Images