IP Library › Granted Patent US 12,547,647
Granted Patent B2
US 12,547,647 · App. 18/207,861 · Granted Feb 10, 2026

Unsupervised machine learning system to automate functions on a graph structure

Inventors: Ronnie J. Morris (Mesquite, TX); Dana M. Pusey-Conlin (Wilmington, DE); Lorraine C. Edkin (Jacksonville, FL); Scott A. Sims (Tega Cay, SC); Joel Filliben (Newark, DE); Margaret A. Payne (Elkton, MD); Craig Douglas Widmann (Chandler, AZ); Eren Kursun (New York, NY)
Assignee: Bank of America Corporation
G06F16/288G06F16/2291
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,547,647
App. No.
18/207,861
Granted
Feb 10, 2026
Kind
B2
Abstract

Machine learning models, semantic networks, adaptive systems, artificial neural networks, convolutional neural networks, and other forms of knowledge processing systems are disclosed. An ensemble machine learning system is coupled to a graph module storing a graph structure, wherein a collection of entities and the relationships between those entities forms nodes and connection arcs between the various nodes. A hotfile module and hotfile propagation engine coordinate with the graph module or may be subsumed within the graph module, and implement the various hot file functionality generated by the machine learning systems.

Claims (39)

1 . A method comprising:

determining data corresponding to one or more graph representations of a first plurality of entities, wherein the one or more graph representations indicate a plurality of relationships between the first plurality of entities;

training, for a first entity type, a first artificial neural network for machine learning executing on one or more first computing devices, wherein the first artificial neural network comprises a plurality of nodes, and wherein the plurality of nodes is configured based on a first portion of the data corresponding to the first entity type;

training, for a second entity type, a second artificial neural network for machine learning executing on the one or more first computing devices, wherein the second artificial neural network comprises a second plurality of nodes, and wherein the second plurality of nodes is configured based on a second portion of the data corresponding to the second entity type;

determining a first graph representation comprising a second plurality of entities, wherein the second plurality of entities comprises a first entity corresponding to the first entity type and a second entity corresponding to the second entity type; and

receiving, from the first artificial neural network and the second artificial neural network and based on the first graph representation, output indicating a modification to a hotfile,

wherein the hotfile comprises a dynamic graph structure representing risk associated with transaction data.

2 . The method of claim 1 , wherein each entity of the second plurality of entities is associated with a corresponding machine learning model.

3 . The method of claim 1 , further comprises determining a characterization of the first graph representation comprising:

transmitting output from the first artificial neural network and the second artificial neural network to a third artificial neural network; and

receiving, from the third artificial neural network, the modification to the hotfile.

4 . The method of claim 1 , wherein the modification to the hotfile is based on historical hotfile data.

5 . The method of claim 1 , wherein the one or more graph representations are associated with one or more transactions between at least two entities of the first plurality of entities.

6 . The method of claim 1 , wherein after the modification to the hotfile, further comprising:

adding or removing a first entity of the first plurality of entities to the hotfile;

adding or removing a first relationship between two entities of the first plurality of entities to the hotfile; or

modifying permissions of the hotfile associated with one or more entities of the first plurality of entities.

7 . The method of claim 1 , further comprising:

determining a transaction between at least two entities of the first plurality of entities; and

causing, based on the hotfile, rejection of the transaction.

8 . An apparatus comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the apparatus to:

determine data corresponding to one or more graph representations of a first plurality of entities, wherein the one or more graph representations indicate a plurality of relationships between the first plurality of entities;

train, for a first entity type, a first artificial neural network for machine learning executing on one or more first computing devices, wherein the first artificial neural network comprises a plurality of nodes, and wherein the plurality of nodes is configured based on a first portion of the data corresponding to the first entity type;

train, for a second entity type, a second artificial neural network for machine learning executing on the one or more first computing devices, wherein the second artificial neural network comprises a second plurality of nodes, and wherein the second plurality of nodes is configured based on a second portion of the data corresponding to the second entity type;

determine a first graph representation comprising a second plurality of entities, wherein the second plurality of entities comprises a first entity corresponding to the first entity type and a second entity corresponding to the second entity type; and

receive, from the first artificial neural network and the second artificial neural network and based on the first graph representation, output indicating a modification to a hotfile,

wherein the hotfile comprises a dynamic graph structure representing risk associated with transaction data.

9 . The apparatus of claim 8 , wherein each entity of the second plurality of entities is associated with a corresponding machine learning model.

10 . The apparatus of claim 8 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:

determine a characterization of the first graph representation comprising:

transmitting output from the first artificial neural network and the second artificial neural network to a third artificial neural network; and

receiving, from the third artificial neural network, the modification to the hotfile.

11 . The apparatus of claim 8 , wherein the modification to the hotfile is based on historical hotfile data.

12 . The apparatus of claim 8 , wherein the one or more graph representations are associated with one or more transactions between at least two entities of the first plurality of entities.

13 . The apparatus of claim 8 , wherein the memory further stores instructions that, when executed by the one or more processors, cause the apparatus to:

determine a transaction between at least two entities of the first plurality of entities; and

cause, based on the hotfile, rejection of the transaction.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 9, 2023
From: MORRIS, RONNIE J.; PUSEY-CONLIN, DANA M.; EDKIN, LORRAINE C.; SIMS, SCOTT A.; FILLIBEN, JOEL; PAYNE, MARGARET A.; WIDMANN, CRAIG DOUGLAS; KURSUN, EREN
To: BANK OF AMERICA CORPORATION
Reel/Frame 063907/0821 →
Continuity (2)
Continuation 16006559 · Jun 12, 2018
Related Publication 20230316076A1 · Oct 5, 2023
References Cited (68)
US 6961734B2 · Kauffman · 2005 [cited by applicant]
US 7171557B2 · Kallahalla et al. · 2007 [cited by applicant]
US 7562814B1 · Shao et al. · 2009 [cited by applicant]
US 7720882B2 · Liu et al. · 2010 [cited by applicant]
US 7836065B2 · Hackmann · 2010 [cited by applicant]
US 7908645B2 · Varghese et al. · 2011 [cited by applicant]
US 8005842B1 · Pasca et al. · 2011 [cited by applicant]
US 8010454B2 · Engel et al. · 2011 [cited by applicant]
US 8037113B2 · Bisht · 2011 [cited by applicant]
US 8086638B1 · Stacey et al. · 2011 [cited by applicant]
US 8296301B2 · Lunde · 2012 [cited by applicant]
US 8296312B1 · Leung et al. · 2012 [cited by applicant]
US 8316008B1 · Kohli · 2012 [cited by applicant]
US 8700684B2 · Kim et al. · 2014 [cited by applicant]
US 8762298B1 · Ranjan et al. · 2014 [cited by applicant]
US 9087088B1 · Bose et al. · 2015 [cited by applicant]
US 9113001B2 · Rajakumar et al. · 2015 [cited by applicant]
US 9547651B1 · Ahmed et al. · 2017 [cited by applicant]
US 9747644B2 · Cowen et al. · 2017 [cited by applicant]
US 10009358B1 · Xie et al. · 2018 [cited by applicant]
US 10628826B2 · Yu et al. · 2020 [cited by applicant]
US 20050024398A1 · Kanamaru · 2005 [cited by applicant]
US 20070174214A1 · Welsh et al. · 2007 [cited by applicant]
US 20100169137A1 · Jastrebski et al. · 2010 [cited by applicant]
US 20110022483A1 · Hammad · 2011 [cited by applicant]
US 20120226590A1 · Love et al. · 2012 [cited by applicant]
US 20160307115A1 · Wu · 2016 [cited by applicant]
US 20170169432A1 · Arvapally et al. · 2017 [cited by applicant]
US 20180113899A1 · Htun et al. · 2018 [cited by applicant]
US 20180150572A1 · Yates et al. · 2018 [cited by applicant]
US 20180330258A1 · Harris et al. · 2018 [cited by applicant]
US 20210027182A1 · Harris et al. · 2021 [cited by applicant]
“1.11. Ensemble Methods”, Scikit learn, date unknown, retrieved from internet May 2, 2018, URL: http://scikit-learn.org/stable/modules/ensemble.html, 20 pp. [cited by applicant]
“A Guide to TF Layers: Building a Convolutional Neural Network”, date unknown, retrieved from internet May 2, 2018, URL: https://www.tensorflow.org/tutorials/layers, 17 pp. [cited by applicant]
“Anomaly Detection Using K-Means Clustering”, Jun. 30, 2015, retrieved from internet May 2, 2018, URL: https://anomaly.io/anomaly-detection-clustering/. [cited by applicant]
“Best of Bai Beacon: Artifical Intelligence”, unknown date, retrieved from internet, URL: https://www.bai.org/events/microsites/bai-beacon—2017-archive/about/best-of-bai-beacon-artifical-intelligence, 4 pp. [cited by applicant]
Avinash, Sharma V., “Understanding Activation Functions in Neural Networks”, Mar. 30, 2017, retrieved from internet May 2, 2018, URL: https://medium.com/the-theory-of-everything/understanding-activation-functions-in-neu… [cited by applicant]
Barta, Dan, “Fighting Payments Fraud the Hybrid Way”, May 9, 2012, 3 pp. [cited by applicant]
Brownlee, Jason, “A Gentle Introduction to the Gradient Boosting Algorithm for Machine Learning”, Sep. 9, 2016, retireved from internet May 2, 2018, URL: https://machinelearningmastery.com/gentle-inttroduction-gradient-… [cited by applicant]
Brownlee, Jason, “Ensemble Machine Learning Algorithms in Python With Scikit-Learn”, Jun. 3, 2016, retrieved from internet May 2, 2018, URL: https://machinelearningmastery.com/ensemble-machine-learning-algorithms-python… [cited by applicant]
Brownlee, Jason, “Gentle Introduction to the Adam Optimization Algorithm for Deep Learning”, Jul. 3, 2017, retrieved from internet May 2, 2018, URL: https://machinelearningmastery.com/adam-optimization-algorithm-for-dee… [cited by applicant]
Frans, Kevin, “Variational Autoencoders Explained”, Aug. 6, 2016, retrieved from internet May 8, 2018, URL: http://kvfrans.com/variational-autoencoders-explained/. [cited by applicant]
Glander, Shirin, “Autoencoders and Anomaly Detection With Machine Learning in Fraud Analytics”, May 1, 2017, retrieved from internet May 2, 2018, URL: https://shiring.github.io/machine_learning/2017/05/01/fraud, 27 pp. [cited by applicant]
Gorman, Ben, “No Free Hunch, a Kaggler's Guide to Model Stacking in Practice”, Dec. 27, 2016. [cited by applicant]
Gulshan, Varun et al., “Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Reintopathy in Retinal Fundus Photographs”, JAMA, Dec. 13, 2016, vol. 316, No. 22, p. 2402-2410. [cited by applicant]
Lyudchik, Olga, “Outlier Detection Using Autoencoders”, Cern non-member state, summer student report, Aug. 19, 2016. [cited by applicant]
Patil, DJ, “Data Jujitsu”, copyright 2012, published by OReilly Media, Inc., 29pp. [cited by applicant]
Ruder, Sebastian, An Overview of Gradient Descent Optimization Algorithms, Jan. 19, 2016, retrieved from internet May 2, 2018, URL: http://ruder.io/optimizing-gradient-descent/, 38 pp. [cited by applicant]
Shahreza, M. Lotfi et al., “Anomaly Detection Using a Self-Organizing Map and Particle Swarm Optimization”, Scientia Iranica, Jan. 18, 2011, 18(6), pp. 1460-1468. [cited by applicant]
Smolykov, Vadim, “Ensemble Learning to Improve Machine Learning Results”, Aug. 22, 2017, retrieved from internet May 2, 2018, URL: https://blog.statsbot.co/ensemble-learning-d'dcd54e936. [cited by applicant]
Wikipedia, “Ensemble Learning”, unknown date, retrieved from internet May 2, 2018, URL: https://en.wikipedia.org/wiki/Ensemble_learning, 7 pp. [cited by applicant]
Wikipedia, “Feature Engineering”, unknown date, retrieved from internet Apr. 24, 2018, URL: https://en.wikipedia.org/wiki/Feature_engineering, 3 pp. [cited by applicant]
Wikipedia, “Self-Organizing Map”, unknown date, retrieved from internet Feb. 27, 2018, URL: https://en.wikipedia.org/wiki/Self-organizing_map, 8 pp. [cited by applicant]
Van Vlasselaer, Veronique, et al. “Gotcha! Network-based fraud detection for social security fraud.” Management Science 63.9 ( 2017): 3090-3110. (Year: 2017). [cited by applicant]
McGlohon, Mary, et al. “Snare: a link analy1ic system for graph labeling and risk detection.” Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. 2009. (Year: 2009). [cited by applicant]
Zhan et al., “A Loan Application Fraud Detection Method Based on Knowledge Graph and Neural Network,” Mar. 2018, ICIAI, Assocation for Computing Machinery, pp. 111-115 (Year: 2018). [cited by applicant]
Tselykh et al., “Web Service for Detecting Credit Card Fraud in Near Real-Time,” Sep. 2015, SIN '15, ACM, 4 pag (Year: 2015). [cited by applicant]
Akoglu et al., “Graph-based Anomaly Detection and Description: A Survey,” Apr. 28, 2014, arXiv:1404.4679v2 [cs.SI], pp. 1-68 (Year: 2014). [cited by applicant]
Monamo etal., “Unsupervised Learning for Robust Bitcoin Detection,” 2016, IEEE, pp. 129-134 (Year: 2016). [cited by applicant]
Apr. 26, 2022—U.S. Advisory Action—U.S. Appl. No. 16/006,285. [cited by applicant]
Olszewski D. “Fraud detection using self-organizing map visualizing the user profiles. Knowledge-Based Systems.”, Nov. 1, 2014 ;70: 324-34. (Year 2014). [cited by applicant]
Shahreza ML, et al. “Anomaly detection using a self-organizing map and particle swarm optimization.”, Scientia Irani ca. Dec. 1, 2011; 18(6): 1460-8. (Year: 2011). [cited by applicant]
Zaslavsky V, et al. “A. Credit card fraud detection using self-organizing maps. Information and Security.” Jan. 2006; 18:48. (Year: 2006). [cited by applicant]
May 25, 2022—U.S. Non-Final Office Action—U.S. Appl. No. 16/006,559. [cited by applicant]
Tuyls, K. et al., “Machine Learning Techniques for Fraud Detection” (Year: 2015). [cited by applicant]
Malini, N. et al., “Analysis on credit card fraud identification techniques based on KNN and outlier detection”, 2017 Third International Conference on Advances in Electrical, Electronics, Information, Communication and… [cited by applicant]
Low, Y. et al., “Distributed Graph Lab: A Framework for Machine Learning and Data Mining in the Cloud” (Year: 2012). [cited by applicant]
Mar. 13, 2023—U.S. Notice of Allowance—U.S. Appl. No. 16/006,559. [cited by applicant]