Target object behavior prediction method for data offset and related equipment thereof

Abstract

The invention belongs to the field of artificial intelligence, and relates to a target object behavior prediction method for data offset and related equipment thereof. The method comprises the steps:acquiring a feature variable, carrying out preprocessing and feature screening, and generating a first feature variable set and a second feature variable set; performing weight assignment on the firstcharacteristic variable set, obtaining a third characteristic variable set according to the second characteristic variable set, and performing weight assignment; performing model training according to the first feature variable set and the corresponding weight to output a training result, and performing model training according to the first feature variable set, the third feature variable set andthe corresponding weight to obtain a training result; and when a comparison result of the two training results meets a preset condition, outputting a second training model to perform behavior prediction. The invention also relates to a blockchain technology, and the behavior prediction result can be stored in a blockchain. According to the scheme, the model risk can be reduced while the model prediction precision is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method, apparatus, computer equipment and storage medium for predicting the behavior of a target object for data offset. Background technique [0002] In the model prediction scenario where the training set and prediction set of the target object have a long time interval, the distribution and prediction ability of the target object's feature variables will fluctuate over time. Such unstable feature variables make the model prediction uncertain. increase, resulting in increased forecast risk. At present, in order to reduce the risk of model prediction, the method of feature selection is used to eliminate unstable feature variables, or to perform information smoothing processing on feature variables. However, these unstable feature variables still contain information that is beneficial to model prediction. The existing solutions The scheme loses t...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiment of the present application is to propose a target object behavior prediction method, device, computer equipment, and storage medium for data offset, so as to solve the loss of information diversity in the process of reducing model risk in the prior art, resulting in The problem of reduced prediction accuracy of the model

Images