Intelligent suspicious transaction monitoring method based on semi-supervised graph neural network

Abstract

The invention discloses an intelligent suspicious transaction monitoring method based on a semi-supervised graph neural network. The method comprises the steps of collecting and storing original transaction flow; constructing a fund transaction network based on a transaction relationship at the account level; dividing accounts in the fund transaction network into different transaction communities;performing risk assessment and screening on the transaction community to generate a high-risk-density fund transaction network; deriving individual transaction characteristics of the account; and inputting the individual transaction characteristics of the high-risk-density fund transaction network and the account into a semi-supervised graph neural network, outputting the fund transaction risk probability of the account by the semi-supervised graph neural network, and judging the account of which the fund transaction risk probability is higher than a first threshold value as a high-money laundering risk account. The method has the advantages that the abnormal risk of an individual account can be judged, an advanced semi-supervised classification model is constructed through deep data mining and graph algorithm mining, and a traditional risk control means can be remarkably improved.

Description

technical field [0001] The invention belongs to the field of financial risks, and in particular relates to an intelligent suspicious transaction monitoring method based on a semi-supervised graph neural network. Background technique [0002] With the popularization of mobile Internet and the rapid development of cross-border trade and transactions, my country is facing increasingly severe capital transaction risks. On the criminal side, abnormal fund transactions, such as anti-money laundering crimes, are constantly evolving to become more concealed, intelligent, and large-scale. However, on the financial institution side, many still remain in the traditional way of relying on the combination of manual verification by experts and rule models. This approach leads to a continual increase in exposure to: [0003] First, manual verification has the problems of low efficiency and high cost. At present, my country is one of the most developed regions in the world for Internet t...

AI Technical Summary

Problems solved by technology

[0004] Second, the accuracy of the traditional rule model is low. According to incomplete statistics, the average false positive rate of industry money laundering risk prediction is as high as 95%.

[0005] Third, it cannot dynamically adapt to the evolution of money laundering risks

Images