# US 2019/0378050 A1 · Machine learning system to identify and optimize features based on historical data, known patterns, or emerging patterns

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0378050 A1
- Document ID: US20190378050A1
- Status: Published application
- Kind: A1
- Application number: 16/006,470
- Filed: 2018-06-12
- Published: 2019-12-12
- Earliest claimed: 2018-06-12
- Assignees: Bank of America Corporation
- Applicants: Bank of America Corporation
- Inventors: Lorraine C. Edkin; Craig Douglas Widmann; Scott A. Sims; Margaret A. Payne; Dana M. Pusey-Conlin; Ronnie J. Morris; Joel Filliben; Eren Kursun
- Web page: https://patentgrep.com/patent/US20190378050A1

## CPC

- G06N 20/00: Machine learning
- G06F 16/285: {Clustering or classification}
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06N 20/20: Ensemble learning
- G06Q 30/0185: {Product, service or business identity fraud}
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## 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

### Claim 1

A supervised machine learning system that optimizes a feature vector and trains on a corpus based on historical data, known patterns, and emerging patterns, the system comprising:
a graph module configured to store and update a graph comprising nodes and edges, wherein each node corresponds to an entity type, and wherein each edge represents a relationship between two nodes;
a first interface configured to receive (i) historical data and (ii) current event data, wherein the (i) and (ii) are used to update the graph;
a second interface configured to receive user input to classify a first set of nodes in the graph with one of a plurality of classifications; and
a machine learning engine programmed to perform steps comprising:
training a machine learning model of the machine learning engine using the corpus, wherein the corpus comprises a training data and a test data;
classifying a plurality of nodes in the graph based on the known patterns and the machine learning model, by setting a classification attribute of each node to one of a plurality of classifications, wherein the plurality of nodes exclude the first set of nodes;
detecting, by the machine learning engine, an emerging pattern between a first node and second node in the graph based on the (i) and (ii);
inserting an edge between the first node and the second node in the graph in response to the detecting of the emerging pattern; and
adjusting the feature vector based on an objective function to minimize a loss function.

### Claim 2 (depends on 1)

The system of claim 1, wherein the machine learning engine comprises a plurality of supervised machine learning engines, wherein each unique entity type in the graph is assigned a separate supervised machine learning engine of the plurality of supervised machine learning engines.

### Claim 3 (depends on 2)

The system of claim 2, wherein the machine learning model corresponds to the supervised machine learning engine assigned to the entity type of the first node.

### Claim 4 (depends on 1)

The system of claim 1, wherein the classifying of the first node in the graph comprises populating a confidence attribute of the first node, based on the machine learning model.

### Claim 5 (depends on 1)

The system of claim 1, wherein the adjusting the feature vector comprises adding a feature to the feature vector.

### Claim 6 (depends on 1)

The system of claim 1, wherein the adjusting the feature vector comprises removing a feature from the feature vector.

### Claim 7 (depends on 1)

The system of claim 1, the system further comprising:
a historical data store communicatively coupled to first interface, wherein the test data comprises the first set of nodes and their corresponding historical data stored in the historical data store.

### Claim 8 (depends on 1)

The system of claim 1, the system further comprising:
a user computing device, which is communicatively coupled to the second interface, configured to transmit a user selection of the one of the plurality of classifications for the first set of nodes in the graph.

### Claim 9 (depends on 1)

The system of claim 1, wherein the graph module, in response to receiving the current event data through the first interface, is configured to set the classification attribute of the plurality of nodes to a value predicted by the machine learning engine.

### Claim 10 (depends on 1)

The system of claim 1, wherein the machine learning engine comprises a graphics processing unit.

### Claim 11 (depends on 1)

The system of claim 1, wherein the machine learning engine is a semi-supervised machine learning engine.

### Claim 12 (depends on 1)

The system of claim 1, wherein the current event data comprises at least one of: new transaction data, a report of a stolen card, an uninstallation of a software application from a device, and an installation of a software application onto a device.

### Claim 13 (depends on 1)

The system of claim 1, wherein the first node stored by the graph module corresponds to a device entity type and the second node stored by the graph module corresponds to a customer entity type, and wherein the edge inserted between the first node and the second node is in response to the machine learning engine detecting the emerging pattern between a customer's smartphone device and fraud.

### Claim 14 (depends on 13)

The system of claim 13, wherein the first node comprises a confidence attribute, and the graph module is configured to update the confidence attribute of the first node based on the machine learning model that detected the emerging pattern.

### Claim 15

A system comprising:
a first interface configured to receive (i) historical data and (ii) current event data;
a graph module configured to update a graph comprising nodes and edges, wherein each node corresponds to an entity type, and wherein each edge represents a relationship between two nodes; and
a supervised machine learning engine programmed to perform steps comprising:
training a machine learning model of the supervised machine learning engine using a corpus, wherein the corpus comprises a training data and a test data;
classifying a plurality of nodes in the graph based on a known pattern and the machine learning model, by setting a classification attribute of each node to one of a plurality of classifications;
detecting, by the supervised machine learning engine, an emerging pattern between a first node and second node of the plurality of nodes in the graph based on at least the (i) and (ii);
inserting an edge between the first node and the second node in the graph in response to the detecting of the emerging pattern; and
adjusting a feature vector of the supervised machine learning engine based on an objective function to minimize a loss function.

### Claim 16 (depends on 15)

The system of claim 15, wherein the supervised machine learning engine is further programmed to optimize a feature vector and train on the corpus.

### Claim 17 (depends on 15)

The system of claim 15, further comprising a second interface configured to receive user input, wherein the detecting step of the supervised machine learning engine is further based on the user input.

### Claim 18 (depends on 15)

The system of claim 15, wherein the classifying of the plurality of noes in the graph comprises populating a confidence attribute of each of the plurality of nodes, based on the machine learning model.

### Claim 19

A non-transitory computer readable medium storing computer-executable instructions that, when executed by a processor, cause a machine learning engine to:
train a machine learning model of the machine learning engine using a corpus, wherein the corpus comprises a training data and a test data;
classify a plurality of nodes in a graph stored in computer memory based on known patterns and the machine learning model, by setting a classification attribute of each node in the graph to one of a plurality of classifications;
detect, by the machine learning engine, an emerging pattern between a first node and second node in the graph based on historical data and current event data;
insert an edge between the first node and the second node in the graph in response to the detecting of the emerging pattern; and
adjust a feature vector of the machine learning engine based on an objective function to minimize a loss function.

### Claim 20 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein the processor comprises a graphics processing unit.
