Data index screening method, device, computer equipment and storage medium

Abstract

The present invention relates to the field of artificial intelligence technology, and provides a data index screening method, device, computer equipment, and storage medium, including: standardizing the user data under the corresponding data index according to the data distribution; generating each standard data according to the standardized processing According to the standard data vector of each user, multiple index feature data in the standard data vector of each user are extracted; multiple first key index feature data are screened according to the correlation index of multiple index feature data; the minimum absolute shrinkage and selection algorithm is adopted Sub-extract a plurality of second key indicator feature data and the index weight of each second key indicator feature data; according to the index weight, use the Monte Carlo simulation method to simulate and train the user level prediction model for many times, and according to the corresponding prediction results of the simulation training from Multiple target key indicator characteristic data are screened out from the second key indicator characteristic data. The invention can screen out the optimal data index, and the screening efficiency of the data index is high.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a data index screening method, device, computer equipment and storage medium. Background technique [0002] In the face of a large number of data indicators, manual screening or traditional correlation analysis and screening methods can easily miss low-saturation but very important data indicators. The wrong choice of data indicators will lead to inaccurate effects of subsequent systems or models. . [0003] Especially when the data indicators are growing geometrically, manual screening or traditional correlation analysis is difficult to find all the potential correlations between a large number of data indicators, and the screened data indicators are mixed with more useless data Indicators, not only will not improve the effect of the model, but the number of selected data indicators is large, and it will easily lead to a very low efficiency of model construction...

AI Technical Summary

Problems solved by technology

[0002] In the face of a large number of data indicators, manual screening or traditional correlation analysis and screening methods can easily miss low-saturation but very important data indicators. The wrong choice of data indicators will lead to inaccurate effects of subsequent systems or models.

[0003] Especially when the data indicators are growing geometrically, manual screening or traditional correlation analysis is difficult to find all the potential correlations between a large number of data indicators, and the screened data indicators are mixed with more useless data Indicators, not only will not improve the effect of the model, but the number of selected data indicators is large, and it will easily lead to very low efficiency of model construction

Images