Suspicious feature discovery method based on transaction network nodes

Abstract

The invention relates to a suspicious feature discovery method (200) based on transaction network nodes. The suspicious feature discovery method comprises the following steps: constructing a user transaction network (201) based on original transaction features; obtaining key nodes (202) from the constructed user transaction network; for each key node, performing transaction feature extraction on each transaction and forming a transaction feature set (203); performing association rule mining on the transaction feature set of each key node and aquring a transaction feature frequent set (204).

Description

technical field [0001] The invention relates to a suspicious feature discovery method based on transaction network nodes. Background technique [0002] At present, in the existing technology, most of the suspicious transaction screenings that exist are manually screened for transaction-related features. The feature dimensions only include a few features such as time and money, and usually do not consider the relationship between various features. Interrelated. [0003] In addition, there are methods based on network discovery in the prior art, and these methods are mainly used to discover the interpersonal relationship between nodes, but do not reflect the important characteristics of the network. [0004] Document CN201410085416 discloses a method and device for mining social relationships based on financial data, in which a financial transaction network is constructed through financial transaction data and the network topology attributes of client users and non-network to...

AI Technical Summary

Problems solved by technology

But there is no extraction and utilization of other relevant features of the network

Images