A method and apparatus for training a model based on a gradient lifting decision tree

Abstract

The invention discloses a model training method and a device based on a gradient lifting decision tree. A GBDT algorithm is divided into two phases. In the former phase, several decision trees are trained by obtaining labeled samples from the data domain of the business scenarios similar to the target business scenarios, and the training residuals generated after the training in the previous phaseare determined. At a later stage, that annotated sample are obtained from the data domain of the target business scenario, and a number of decision trees are continue to be trained based on the training residuals. Finally, the model applied to the target business scenario is actually integrated from the decision tree trained in the previous stage and the decision tree trained in the next stage.

Description

Technical field [0001] The embodiments of this specification relate to the field of information technology, and in particular to a model training method and device based on a gradient boosting decision tree. Background technique [0002] As we all know, when it is necessary to train a predictive model applied to a certain business scenario, it is usually necessary to obtain a large amount of data from the data domain of the business scenario for labeling, as a labeled sample, for model training. If the number of labeled samples is small, a qualified model cannot usually be obtained. It should be noted that the data domain of a certain business scenario is actually a collection of business data generated based on the business scenario. [0003] However, in practice, less data is accumulated in certain special business scenarios. As a result, when it is necessary to train a model applied to a certain special business scenario, it is impossible to obtain enough labeled samples from ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem that a qualified model cannot be trained due to the lack of accumulated data in some special business scenarios, the embodiment of this specification provides a model training method and device based on a gradient boosting decision tree. The technical solution is as follows:

Images