Transaction fraud detecting method and system, medium and equipment aiming at abnormal repetition

Abstract

The invention discloses a transaction fraud detecting method and system, a medium and transaction fraud detecting equipment aiming at abnormal repetition. The transaction fraud detecting method comprises the following steps: acquiring transaction record information and transaction identity information; establishing an identify authentication model according to the transaction identity information;extracting real-time transaction identity information, transaction time information and transaction amount information according to the transaction record information; saving the real-time transaction identity information, and analyzing IP information of the real-time transaction identity information; matching the identity authentication model and the real-time transaction identity information toacquire historical matching information; analyzing transaction time information and transaction amount information corresponding to a transaction behaviour corresponding to the historical matching information according to the historical matching information to acquire release identity determination information; updating an identity information model according to the release identity determinationinformation. According to the transaction fraud detecting method, the transaction fraud detecting system, the medium and the transaction fraud detecting equipment aiming at the abnormal repetition, the technical problems of slight low monitoring precision, low detecting effectiveness and long response time in the prior art are solved.

Description

technical field [0001] The invention relates to a transaction behavior monitoring method, in particular to a fraud detection method, system, medium and equipment for abnormal and repeated transactions. Background technique [0002] With the rapid development of Internet technology and electronic transaction technology, network security issues have also become issues closely related to the country, society, and individuals. Nowadays, many criminals are trying to defraud users' personal property by various means, posing a threat to the security of electronic transactions. If this kind of security problem cannot be solved, it will seriously affect the user's trust in the electronic trading platform. Therefore, it is of great practical significance to study how to build a safe and credible online trading platform. Existing fraud detection technologies mainly include two types: one is to detect transactions based on the dominant features of the transactions, and the other is to ...

AI Technical Summary

Problems solved by technology

The problem of the former is that the existing technology does not select features with sufficient discrimination, and often fails to achieve the ideal detection effect; although the latter is better than the former in terms of effect, it often takes more time to mine the hidden features of transactions. There are many machine resources, and it takes a long time, which is contrary to the real-time requirements of electronic exchanges, and also brings more costs to electronic trading platforms

Existing technologies cannot simultaneously find more discriminative hidden features and meet real-time requirements

The vast majority of fraudulent transactions today can be attributed to identity theft. Criminals pretend to be users to operate their accounts. Traditional technology lacks mining and statistics of real data from the perspective of transaction sequences, and it is difficult to extract distinguishable hidden feature

The detection effect of the traditional dominant feature technology is poor, which cannot meet the real-time requirements of the trading system

The transaction data of the electronic trading system cannot be reviewed immediately, and there is a delay in the returned interception / release information

[0003] In summary, the existing technology of transaction fraud detection technology has the technical problems of low detection accuracy and low detection efficiency

Images