US 12,229,782 B2
Network based features for financial crime detection
Wayne B. Shoumaker, San Francisco, CA (US); Harsh Singhal, Charlotte, NC (US); Suhas Sreehari, Berkeley, CA (US); Agus Sudjianto, Charlotte, NC (US); and Ye Yu, San Francisco, CA (US)
Assigned to Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Apr. 19, 2023, as Appl. No. 18/136,557.
Application 18/136,557 is a continuation of application No. 16/714,027, filed on Dec. 13, 2019, granted, now 11,640,609.
Prior Publication US 2023/0252480 A1, Aug. 10, 2023
Int. Cl. G06Q 20/40 (2012.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06Q 20/10 (2012.01); G06Q 40/02 (2023.01); G06Q 50/00 (2024.01); G06Q 40/00 (2023.01)
CPC G06Q 20/4016 (2013.01) [G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06Q 20/10 (2013.01); G06Q 40/02 (2013.01); G06Q 50/01 (2013.01); G06Q 40/00 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A machine learning method implemented by a computing system of a financial institution, the method comprising:
generating, by the computing system, based on a plurality of data records accessed via an electronic database, a network model including a set of financial entities and relationships therebetween, generation of the network model comprising generating an adjacency matrix;
retrieving, by the computing system, from the electronic database, a plurality of financial entity risk vectors monitored by the financial institution;
generating, by the computing system, graphical network features by multiplying financial entity risk vectors by the adjacency matrix of the network model, the adjacency matrix being a function of discrete time, the financial entity risk vectors multiplied by the adjacency matrix according to a plurality of propagation steps;
generating, by the computing system, a training dataset using the graphical network features and a corresponding set of labels generated based on historical data associated with the set of financial entities;
training, by the computing system and based on a supervised learning process, a machine learning predictive model using the graphical network features and the corresponding set of labels of the training dataset to generate predictions of financial crimes, the machine learning predictive model comprising a density-based clustering technique that is a function of a density parameter;
executing, by the computing system, the machine learning predictive model using at least a portion of a second set of graphical network features as input to generate a prediction of a financial crime; and
generating, by the computing system, a perceptible alert on one or more computing devices in response to the prediction of the financial crime, the perceptible alert identifying a subset of the set of financial entities involved in the financial crime as part of a graphical representation of at least a portion of the network model, the graphical representation indicating at least one connection between nodes in the network model, the perceptible alert comprising an interactive update button that causes the perceptible alert to be updated with subsequent data corresponding to the subset.