Method and device for building classification forecasting mixed model

Abstract

The invention discloses a method and a device for building a classification forecasting mixed model. The method includes: dividing a sample data set into data sets of different types according to data characteristics, performing data cleaning for the data sets and performing variable selection after data cleaning is finished to generate variable sets of different types, and adopting at least one classification forecasting single model for each variable set to build the classification forecasting mixed model. Through the method and the device, the classification forecasting mixed model is respectively built after data subdivision, and accuracy of classification forecasting is improved.

Description

technical field [0001] The invention mainly relates to the field of data processing, in particular to a method and device for establishing a classification and prediction mixed model. Background technique [0002] The database is rich in content and contains a large amount of information, which can be used as the basis for intelligent business decision-making, classification and forecasting, and can be used to extract models describing important data categories or predict future data trends. Classification prediction is to use classification models. Classification prediction, classification prediction is binary classification in most cases, for example, the target model can classify the impact of a customer on market influence activities as possible or impossible; the customer churn model may classify users as churners or non-churners, etc. Wait. [0003] Such as figure 1 As shown, the classification prediction model includes three typical steps: training phase, validation...

AI Technical Summary

Problems solved by technology

[0008] In the process of realizing the present invention, the inventor found that there are at least the following disadvantages in the prior art: the classification prediction in the prior art adopts a single classification prediction method, and when it is applied to actual business data, the model is established according to the classification prediction algorithm , due to the limitations of the algorithm itself, a single classification prediction algorithm cannot achieve a good prediction accuracy. At the same time, the existing algorithms and prediction models are executed sequentially in memory, and they are all run on a single machine. The application of the algorithm is limited by the amount of data. Limitation, when the amount of data is large, the existing algorithms and classification prediction models are often time-consuming

Images