Classification model training method and device, computer equipment and storage medium

Abstract

The invention discloses a classification model training method, which is applied to the technical field of artificial intelligence and is used for solving the technical problems of high model training difficulty and inaccurate prediction result when an existing prediction model is used for predicting a low-risk probability event. The method provided by the invention comprises the following steps: acquiring risk training samples and non-risk samples; determining the number of base classifiers; determining a first training sample for training a first base classifier; binning the non-risk samples relative to the current base classifier according to the loss of each non-risk sample, and calculating the weight of each box under the current base classifier; according to the weight of each box and the number of the risk training samples; carrying out sampling from the corresponding boxes according to the determined number, and obtaining training samples of the current base classification; and training the first base classifier through the first training sample, and training the corresponding base classifiers through the training sample of the current base classification to obtain a trained classification model.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a training method, device, computer equipment and storage medium for a classification model. Background technique [0002] Anti-fraud risk control refers to predicting the emergence of risks through relevant technical means before the advent of risks, so that people can intelligently warn unknown risks. Common anti-fraud risk control scenarios include: counterfeit certificate anti-fraud, face detection, identification of high-risk users based on customer historical data, big data anti-money laundering, etc. [0003] In most risk control scenarios, compared with the normal situation, the labels of normal samples and the labels of target samples often show an extremely unbalanced distribution due to the fact that there are very few risks. In many projects or scenarios, the risk control target sample rate is even lower than 0.3%, which means that in 1000 samples, th...

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a classification model training method, device, computer equipment, and storage medium to solve the tec

Images