METHOD AND SYSTEM FOR IDENTIFYING ONLINE MONEY-LAUNDERING CUSTOMER GROUPS
One embodiment provides a method and system for detecting online money laundering. During operation, the system can obtain, from an online financial platform, online financial transaction records associated with a plurality of customer accounts and establish fund-transfer relationships among the plurality of customer accounts based on the transaction records. The system can further perform a cluster-analysis operation to group the plurality of customer accounts into a number of clusters based on the established fund-transfer relationships and apply a machine-learning model to determine whether a respective customer-account cluster is involved in online money laundering.
1 . A computer-executable method, comprising:
obtaining, by a computer from an online financial platform, online financial transaction records associated with a plurality of customer accounts of the online financial platform;
establishing fund-transfer relationships among the plurality of customer accounts based on the transaction records;
performing, by a computer, a cluster-analysis operation to group the plurality of customer accounts into a number of clusters based on the established fund-transfer relationships; and
applying a machine-learning model to determine whether a respective customer-account cluster is involved in online money laundering.
2 . The method of claim 1 , further comprising training the machine-learning model using labeled data associated with a set of sample customer-account clusters.
3 . The method of claim 2 , wherein the machine-learning model comprises a binary-classification model, and wherein training the binary-classification model comprises labeling a first number of sample customer-account clusters as blacklisted and a second number of sample customer-account clusters as whitelisted.
4 . The method of claim 3 , wherein labeling a respective sample customer-account cluster as blacklisted comprises:
determining that a number of customer accounts within the respective sample customer-account cluster are known money-laundering customer accounts; and
in response to a ratio of the known money-laundering customer accounts within the respective sample customer-account cluster exceeding a predetermined threshold, labeling the respective sample customer-account cluster as blacklisted.
5 . The method of claim 1 , further comprising:
extracting a feature vector from the respective customer-account cluster; and
using the feature vector as an input to the machine-learning model.
6 . The method of claim 1 , wherein establishing the fund-transfer relationships among the plurality of customer accounts comprises constructing a fund-transfer graph based on the transaction records, wherein a respective node in the fund-transfer graph corresponds to a customer account, and wherein an edge in the fund-transfer graph corresponds to a fund-transfer relationship between two customer accounts.
7 . The method of claim 6 , further comprising:
constructing a subgraph for each cluster; and
extracting a feature vector from the subgraph using a technique based on detection of network motifs within the subgraph.
8 . The method of claim 1 , wherein establishing the fund-transfer relationships comprises determining whether a fund-transfer relationship exists between two customer accounts based on a total amount of funds transferred between the two customer accounts.
9 . The method of claim 8 , wherein establishing the fund-transfer relationships comprises determining a direction of the fund-transfer relationship between the two customer accounts, and wherein the determined direction includes one of: a first direction, a second opposite direction, and a bi-direction.
10 . The method of claim 1 , wherein performing the cluster-analysis operation comprises implementing a label propagation algorithm (LPA) or a k-means clustering algorithm.
11 . A computer system, comprising:
a processor; and
a storage device coupled to the processor and storing instructions which when executed by the processor cause the processor to perform a method, the method comprising:
obtaining, from an online financial platform, online financial transaction records associated with a plurality of customer accounts of the online financial platform;
establishing fund-transfer relationships among the plurality of customer accounts based on the transaction records;
performing, by a computer, a cluster-analysis operation to group the plurality of customer accounts into a number of clusters based on the established fund-transfer relationships; and
applying a machine-learning model to determine whether a respective customer-account cluster is involved in online money laundering.
12 . The computer system of claim 11 , wherein the method further comprises training the machine-learning model using labeled data associated with a set of sample customer-account clusters.
13 . The computer system of claim 12 , wherein the machine-learning model comprises a binary-classification model, and wherein training the binary-classification model comprises labeling a first number of sample customer-account clusters as blacklisted and a second number of sample customer-account clusters as whitelisted.
14 . The computer system of claim 13 , wherein labeling a respective sample customer-account cluster as blacklisted comprises:
determining that a number of customer accounts within the respective sample customer-account cluster are known money-laundering customer accounts; and
in response to a ratio of the known money-laundering customer accounts within the respective sample customer-account cluster exceeding a predetermined threshold, labeling the respective sample customer-account cluster as blacklisted.
15 . The computer system of claim 11 , wherein the method further comprises:
extracting a feature vector from the respective customer-account cluster; and
using the feature vector as an input to the machine-learning model.
16 . The computer system of claim 11 , wherein establishing the fund-transfer relationships among the plurality of customer accounts comprises constructing a fund-transfer graph based on the transaction records, wherein a respective node in the fund-transfer graph corresponds to a customer account, and wherein an edge in the fund-transfer graph corresponds to a fund-transfer relationship between two customer accounts.
17 . The computer system of claim 16 , wherein the method further comprises:
constructing a subgraph for each cluster; and
extracting a feature vector from the subgraph using a technique based on detection of network motifs within the subgraph.
18 . The computer system of claim 11 , wherein establishing the fund-transfer relationships comprises determining whether a fund-transfer relationship exists between two customer accounts based on a total amount of funds transferred between the two customer accounts.
19 . The computer system of claim 18 , wherein establishing the fund-transfer relationships comprises determining a direction of the fund-transfer relationship between the two customer accounts, and wherein the determined direction includes one of: a first direction, a second opposite direction, and a bi-direction.
20 . The computer system of claim 11 , wherein performing the cluster-analysis operation comprises implementing a label propagation algorithm (LPA) or a k-means clustering algorithm.