# US 2025/0094853 A1 · Machine learning framework and method for using the same

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

- Number: US 2025/0094853 A1
- Document ID: US20250094853A1
- Status: Published application
- Kind: A1
- Application number: 16/917,624
- Filed: 2020-06-30
- Published: 2025-03-20
- Earliest claimed: 2020-06-30
- Assignees: Stripe, Inc.
- Applicants: Stripe, Inc.
- Inventors: Tianshi Zhu; Erik Osheim; Thomas Switzer; Stephanie Bian; David Abrahams; Susan Tu; Patrick Boykin
- Web page: https://patentgrep.com/patent/US20250094853A1

## CPC

- G06N 20/00: Machine learning
- G06Q 30/04: Billing or invoicing
- G06F 8/451: {Code distribution (considering CPU load at run-time G06F9/505; load rebalancing G06F9/5083)}
- G06F 8/453: {Data distribution}
- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06F 16/24568: {Data stream processing; Continuous queries}
- G06Q 20/027: {involving a payment switch or gateway}
- G06Q 20/0855: {involving a third party}
- G06Q 20/102: {Bill distribution or payments}
- G06Q 20/12: specially adapted for electronic shopping systems
- G06Q 20/34: using cards, e.g. integrated circuit [IC] cards or magnetic cards
- G06Q 20/385: {using an alias or single-use codes}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/06: Buying, selling or leasing transactions
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A machine learning framework and method for using the same are described. In one embodiment, the method for processing data with a machine learning framework comprises creating a plurality of features as independent features, each feature of the plurality features being based on one or more events that model a plurality of records related to payment processing information, creating a final feature that groups the plurality of features together, such that each feature of the plurality of features represents a sub-feature of the final feature, compiling the plurality of features and the final feature, computing, using a computing platform, each of the plurality of features as a separate job, including sending network related communications to access the payment processing information from one or more remote storage locations, and computing, using a computing platform, the final feature separately from computing the plurality of features, including grouping results of running each of the plurality of features together.

## Claims

### Claim 1

A method for processing data with a machine learning framework, the method comprising:
creating a plurality of features as independent features, each feature of the plurality features being based on one or more events that model a plurality of records related to payment processing information;
creating a final feature that groups the plurality of features together, such that each feature of the plurality of features represents a sub-feature of the final feature;
compiling the plurality of features and the final feature;
computing, using a computing platform, each of the plurality of features as a separate job, including sending network related communications to access the payment processing information from one or more remote storage locations;
computing, using a computing platform, the final feature separately from computing the plurality of features, including grouping results of running each of the plurality of features together.

### Claim 2 (depends on 1)

The method defined in claim 1 wherein running each of the plurality of features as a separate job comprises running two or more features of the plurality of features in parallel.

### Claim 3 (depends on 1)

The method defined in claim 1 wherein the features of the plurality of features and final features are user specified via an application programming interface (API).

### Claim 4 (depends on 1)

The method defined in claim 1 further comprising updating one or more predictive models using a result from computing the final feature.

### Claim 5 (depends on 1)

The method defined in claim 1 further comprising:
after computing the final feature,
storing separately, for each feature in the plurality of features, results from computing said each feature; and
enabling access to one or more of the results from computing each feature of the plurality feature for individual use by another feature other than the final feature.

### Claim 6 (depends on 1)

The method defined in claim 1 wherein data from computing the plurality of features is stored in columnar format, and wherein grouping results of running each of the plurality of features together as part of computing the final feature is made, at least in part, based on the columnar format.

### Claim 7 (depends on 1)

The method defined in claim 1 wherein at least one event of the one or more events of at least one feature of the plurality of features perform a lookup to attached a value of another feature to a feed in the at least one event.

### Claim 8 (depends on 7)

The method defined in claim 7 wherein the lookup retains all the information associated with an event.

### Claim 9 (depends on 7)

The method defined in claim 7 wherein the lookup retains only a key associated with an event.

### Claim 10 (depends on 1)

The method defined in claim 1 further comprising obtaining at least one feature of the plurality of features by aggregating events of the one or more events.

### Claim 11

A system system comprising:
a network interface;
a memory to store instructions;
one or more processors coupled to the memory and the network interface to execute the stored instructions to:
create a plurality of features as independent features, each feature of the plurality features being based on one or more events that model a plurality of records related to payment processing information;
create a final feature that groups the plurality of features together, such that each feature of the plurality of features represents a sub-feature of the final feature;
compile the plurality of features and the final feature;
compute, using a computing platform, each of the plurality of features as a separate job, including sending network related communications to access the payment processing information from one or more remote storage locations;
compute, using a computing platform, the final feature separately from computing the plurality of features, including grouping results of running each of the plurality of features together.

### Claim 12 (depends on 11)

The system defined in claim 11 wherein each of the plurality of features are computed as a separate job by running two or more features of the plurality of features in parallel.

### Claim 13 (depends on 11)

The system defined in claim 11 wherein the features of the plurality of features and final features are user specified via an application programming interface (API).

### Claim 14 (depends on 11)

The system defined in claim 11 wherein the one or more processor are operable to update one or more predictive models using a result from computing the final feature.

### Claim 15 (depends on 11)

The system defined in claim 11 wherein the one or more processor are operable to, after computing the final feature,
store separately, for each feature in the plurality of features, results from computing said each feature; and
enable access to one or more of the results from computing each feature of the plurality feature for individual use by another feature other than the final feature.

### Claim 16 (depends on 11)

The system defined in claim 11 wherein data from computing the plurality of features is stored in columnar format, and wherein grouping results of running each of the plurality of features together as part of computing the final feature is made, at least in part, based on the columnar format.

### Claim 17 (depends on 11)

The system defined in claim 11 wherein at least one event of the one or more events of at least one feature of the plurality of features perform a lookup to attached a value of another feature to a feed in the at least one event.

### Claim 18 (depends on 17)

The system defined in claim 17 wherein the lookup retains all the information associated with an event.

### Claim 19 (depends on 17)

The system defined in claim 17 wherein the lookup retains only a key associated with an event.

### Claim 20 (depends on 11)

The system defined in claim 11 wherein the one or more processor are operable to obtain at least one feature of the plurality of features by aggregating events of the one or more events.

### Claim 21

One or more non-transitory computer readable storage media having instructions stored thereupon which, when executed by a machine learning framework having at least a processor and a memory therein, cause the framework to perform operations comprising:
creating a plurality of features as independent features, each feature of the plurality features being based on one or more events that model a plurality of records related to payment processing information;
creating a final feature that groups the plurality of features together, such that each feature of the plurality of features represents a sub-feature of the final feature;
compiling the plurality of features and the final feature;
computing, using a computing platform, each of the plurality of features as a separate job, including sending network related communications to access the payment processing information from one or more remote storage locations;
computing, using a computing platform, the final feature separately from computing the plurality of features, including grouping results of running each of the plurality of features together.

### Claim 22 (depends on 21)

The storage media defined in claim 21 wherein running each of the plurality of features as a separate job comprises running two or more features of the plurality of features in parallel.

### Claim 23 (depends on 21)

The storage media defined in claim 21 wherein the features of the plurality of features and final features are user specified via an application programming interface (API).

### Claim 24 (depends on 21)

The storage media defined in claim 21 further comprising updating one or more predictive models using a result from computing the final feature.

### Claim 25 (depends on 21)

The storage media defined in claim 21 wherein at least one event of the one or more events of at least one feature of the plurality of features perform a lookup to attached a value of another feature to a feed in the at least one event.
