A transaction monitoring method and device

Abstract

The embodiment of the invention relates to the technical field of data processing, in particular to a transaction monitoring method and a transaction monitoring device, which are used for improving the recognition capability of abnormal transaction behaviors. The method provided by the embodiment of the invention comprises the steps of obtaining monitoring transaction flow in a monitoring time period; forming a transaction directed graph by utilizing the monitoring transaction flow, determining suspicious transaction communities from the transaction directed graph, and enabling one suspicioustransaction community to comprise a plurality of suspicious transaction subjects; and for any suspicious transaction subject, calculating an abnormal risk value of the suspicious transaction subject by using an abnormal transaction algorithm model according to the monitoring transaction flow of the suspicious transaction subject, and performing clustering on the suspicious transaction subject by using the abnormal transaction algorithm model to obtain a training sample set which is similar to the training sample set which is obtained by not depending on labels.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a transaction monitoring method and device. Background technique [0002] Criminals may use bank cards, third-party payment and other channels to quickly transfer illegal funds when they commit crimes such as underground banks, telecommunication fraud, gambling, and drugs. With the rapid development of cutting-edge technologies such as big data and artificial intelligence, criminal methods such as money laundering, illegal foreign exchange purchases, and terrorist financing are constantly being refurbished. challenge. [0003] At present, the detection of suspicious and abnormal transactions by domestic financial institutions mainly relies on regulatory documents such as the "Administrative Measures for Large-Amount Suspicious Transactions and Suspicious Transaction Reports of Financial Institutions", designs or derives large-amount and suspicious transaction monitoring ...

AI Technical Summary

Problems solved by technology

[0004] For this rule-based transaction monitoring method, since it is necessary to extract features based on known real cases and set up targeted rule models for different abnormal transaction scenarios, the monitoring effect on unknown abnormal transaction methods is not ideal; and the rules are difficult to cover abnormal transaction behaviors All the complex associations between accounts in the middle account, and the ability to identify abnormal transaction behavior is limited

Images