Machine-learning techniques for risk assessment based on clustering

Patent metadata

Field	Value
Publication number	US-12579446-B2
Application number	US-202218057147-A
Country	US
Kind code	B2
Filing date	Nov 18, 2022
Priority date	Nov 19, 2021
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

Systems and methods for predicting future risk for a target entity are provided. A risk assessment system receives historical risk assessment data of the target entity and identifies a target cluster that matches the historical risk assessment data. The target cluster is identified from a group of clusters determined using high dimensional clustering based on risk assessment data of a set of entities. The risk assessment system identifies a set of nearest neighbors of the target cluster and determines a prediction of future risk for the target entity based on the target cluster and the set of nearest neighbors. The risk assessment system transmits a responsive message, which can include the prediction of future risk, to a remote computing device for use in controlling access of the target entity to one or more interactive computing environments.

First claim

What is claimed is:

1 . A method comprising:
receiving, by a processing device, historical risk assessment data of a target entity; identifying, by the processing device, a target cluster out of a plurality of clusters, the target cluster matching the historical risk assessment data of the target entity, wherein the plurality of clusters are determined based on risk assessment data of a plurality of entities using high dimensional clustering; identifying, by the processing device and from the plurality of clusters, a set of nearest neighboring clusters of the target cluster; determining, by the processing device, a prediction of risk for the target entity based on the target cluster and the set of nearest neighboring clusters; and transmitting, by the processing device and to a remote computing device, a responsive message including at least the prediction of risk for use in controlling access of the target entity to one or more interactive computing environments.

2 . The method of claim 1 , wherein determining the prediction of risk for the target entity comprises determining, by the processing device, the prediction of risk using a center path of the target cluster of the plurality of clusters.

3 . The method of claim 1 , wherein the target cluster of the plurality of clusters includes a plurality of micro paths, and wherein determining the prediction of risk for the target entity comprises determining the prediction of risk using a micro path of the plurality of micro paths.

4 . The method of claim 3 , wherein the historical risk assessment data comprises historical risk indicator data, and wherein determining the prediction of risk using the micro path comprises:
identifying, among the target cluster and the set of nearest neighboring clusters, a plurality of micro paths; determining that a particular micro path of the plurality of micro paths has the smallest distance to the historical risk indicator data; and determining the prediction of risk using the particular micro path.

5 . The method of claim 3 , wherein each micro path of the plurality of micro paths comprises a plurality of percentile paths, wherein each percentile path of the plurality of percentile paths follows a trend of risk indicator values of a particular percentile of the plurality of entities, and wherein the method further comprises:
determining, by the processing device, a particular percentile path of the plurality of percentile paths that has the smallest distance with respect to the risk indicator values.

6 . The method of claim 5 , wherein determining the prediction of risk using the micro path comprises determining the prediction of risk using the particular percentile path of the plurality of percentile paths.

7 . The method of claim 1 , wherein identifying the target cluster of the plurality of clusters comprises:
determining a plurality of distances, the plurality of distances measuring respective distances between the plurality of clusters and the historical risk assessment data; determining that a distance between a particular cluster and the historical risk assessment data is a smallest distance among the plurality of distances; and determining the particular cluster as the target cluster.

8 . A system comprising:
a processor; and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform operations comprising:
receiving historical risk assessment data of a target entity;
identifying a target cluster out of a plurality of clusters, the target cluster matching the historical risk assessment data of the target entity, wherein the plurality of clusters are determined based on risk assessment data of a plurality of entities using high dimensional clustering;
identifying, from the plurality of clusters, a set of nearest neighboring clusters of the target cluster;
determining a prediction of risk for the target entity based on the target cluster and the set of nearest neighboring clusters; and
transmitting, to a remote computing device, a responsive message including at least the prediction of risk for use in controlling access of the target entity to one or more interactive computing environments.

9 . The system of claim 8 , wherein the operation of determining the prediction of risk for the target entity comprises determining the prediction of risk using a center path of the target cluster of the plurality of clusters.

10 . The system of claim 8 , wherein the target cluster of the plurality of clusters includes a plurality of micro paths, and wherein the operation of determining the prediction of risk for the target entity comprises determining the prediction of risk using a micro path of the plurality of micro paths.

11 . The system of claim 10 , wherein the historical risk assessment data comprises historical risk indicator data, and wherein the operation of determining the prediction of risk using the micro path comprises:
identifying, among the target cluster and the set of nearest neighboring clusters, a plurality of micro paths; determining that a particular micro path of the plurality of micro paths has the smallest distance to the historical risk indicator data; and determining the prediction of risk using the particular micro path.

12 . The system of claim 10 , wherein each micro path of the plurality of micro paths comprises a plurality of percentile paths, wherein each percentile path of the plurality of percentile paths follows a trend of risk indicator values of a particular percentile of the plurality of entities, and wherein the operations further comprise:
determining a particular percentile path of the plurality of percentile paths that has the smallest distance with respect to the risk indicator values.

13 . The system of claim 12 , wherein the operation of determining the prediction of risk using the micro path comprises determining the prediction of risk using the particular percentile path of the plurality of percentile paths.

14 . The system of claim 8 , wherein the operation of identifying the target cluster of the plurality of clusters comprises:
determining a plurality of distances, the plurality of distances measuring respective distances between the plurality of clusters and the historical risk assessment data; determining that a distance between a particular cluster and the historical risk assessment data is a smallest distance among the plurality of distances; and determining the particular cluster as the target cluster.

15 . A non-transitory computer-readable medium comprising instructions that are executable by a processing device for causing the processing device to perform operations comprising:
receiving historical risk assessment data of a target entity; identifying a target cluster out of a plurality of clusters, the target cluster matching the historical risk assessment data of the target entity, wherein the plurality of clusters are determined based on risk assessment data of a plurality of entities using high dimensional clustering; identifying, from the plurality of clusters, a set of nearest neighboring clusters of the target cluster; determining a prediction of risk for the target entity based on the target cluster and the set of nearest neighboring clusters; and transmitting, to a remote computing device, a responsive message including at least the prediction of risk for use in controlling access of the target entity to one or more interactive computing environments.

16 . The non-transitory computer-readable medium of claim

Assignees

• Equifax Inc

Inventors

• Patel Piyush
• Bondugula Rajkumar

Classifications

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N20/00 Primary

  Machine learning · CPC title