Abnormal user identification method and device, storage medium and electronic equipment

Abstract

The invention relates to the technical field of data analysis. The invention provides an abnormal user identification method. The method comprises the following steps: constructing a weighted fully connected graph for to-be-detected user group data; finding out risk nodes in the connected graph and finding out nodes associated with the risk nodes; and taking the nodes associated with the risk nodes and the risk nodes as suspicious nodes, determining communities where the suspicious nodes are located based on a community discovery algorithm, performing risk scoring on the communities where thesuspicious nodes are located, and finally determining abnormal user groups from the to-be-detected user groups. According to the embodiment of the invention, when the artificial intelligence technology is used for abnormal user identification, the recall rate and accuracy of risk identification are effectively improved, and the application field range of the risk monitoring method is expanded.

Description

technical field [0001] The present application relates to the technical field of data analysis, and specifically relates to an abnormal user identification method, an abnormal user identification device, a computer-readable storage medium, and electronic equipment. Background technique [0002] With the rise and vigorous development of the artificial intelligence (AI) boom, artificial intelligence technology is playing an increasingly important role in the field of financial anti-fraud, anti-money laundering and anti-fraud, hereinafter referred to as abnormality or risk. However, there are technical difficulties in using AI technology to detect risks such as fraud and money laundering, with few or no labels. Therefore, unsupervised learning technology is almost the only option. Among them, the three most widely used mainstream unsupervised learning algorithms are: Clustering algorithms, outlier detection algorithms, and complex network algorithms. [0003] However, the abov...

AI Technical Summary

Problems solved by technology

[0003] However, the above three algorithms have their own defects and deficiencies in artificial intelligence (AI) risk detection. For example, there is usually no necessary connection between the groups divided by the clustering algorithm and the abnormalities; Positive rate) is too high, it is easy to accidentally injure good customers; the lack of strong relationship attributes in complex network algorithms or uneven data quality makes it difficult for complex networks to play a good role in the field of risk identification

Therefore, when abnormal user identification exists in the prior art, the recall rate and precision rate of risk identification are low, and the application field of risk monitoring method is small.

Images