Risk identification model training method and device and server

Abstract

The embodiment of the invention provides a risk identification model training method. Due to the fact that different types of unsupervised machine learning algorithms have different requirements for characteristics, the type of the target unsupervised machine learning algorithm can be firstly determined, then various types of characteristic information are extracted from input information, and then target characteristic information is extracted from the characteristic information according to a characteristic extraction mode corresponding to the type of the target unsupervised machine learningalgorithm. Due to the fact that the target characteristic information matched with the target unsupervised machine learning algorithm is extracted, the target characteristic information is trained based on the target unsupervised machine learning algorithm, the identification precision of the obtained target risk identification model corresponding to the target unsupervised machine learning algorithm is higher, and the risk identification accuracy is ensured.

Description

technical field [0001] The embodiment of this specification relates to the field of Internet technologies, and in particular to a risk identification model training method, device and server. Background technique [0002] With the rapid development of the Internet, more and more services can be realized through the Internet, such as online payment, online shopping, online transfer and other Internet services. While the Internet provides convenience to people's lives, it also brings risks. One type of risk is mainly the transactions that users conduct through their own accounts for the purpose of obtaining illegal benefits. These transactions themselves are often false because they are not for the purpose of actual purchase. This type of risk is called false transaction risk. The identification of false transactions is an important part and cornerstone of financial security, but such risks are usually difficult to obtain the historical transaction labels of bad actors, so th...

AI Technical Summary

Problems solved by technology

The identification of false transactions is an important part and cornerstone of financial security, but such risks are usually difficult to obtain the historical transaction labels of bad actors, so the identification of false transactions is an unsupervised machine learning problem

Images